Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 13895
    Prev
    Next
    INDEX
    Explanations

    references to musical themes and components in film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    text related to theater, opera, drama, and performing arts, especially in non-English languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @danielepoterti
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helm
    -0.15
    .hl
    -0.15
     blast
    -0.15
    ocz
    -0.14
    ANNEL
    -0.14
     Blast
    -0.14
    DP
    -0.14
    assis
    -0.14
    jon
    -0.14
     filmmakers
    -0.14
    POSITIVE LOGITS
     ballet
    0.25
     oper
    0.24
     lib
    0.24
     libre
    0.24
     pant
    0.24
     опеÑĢа
    0.24
     tragedy
    0.23
     drama
    0.22
     opera
    0.22
     scenarios
    0.22
    Activations Density 0.040%

    No Known Activations