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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 18294
    Prev
    Next
    INDEX
    Explanations

    references to goats and their distinct physical characteristics, particularly horns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ency
    -0.17
    ifting
    -0.16
    ift
    -0.14
    iating
    -0.14
    iconductor
    -0.14
    ively
    -0.14
    icens
    -0.14
     Petersburg
    -0.14
    ationship
    -0.13
    боÑĤ
    -0.13
    POSITIVE LOGITS
    UNT
    0.16
    utan
    0.16
    tach
    0.15
    rim
    0.15
    sse
    0.15
    ¼
    0.15
    edir
    0.14
    igos
    0.14
    pipes
    0.14
    имÑĥ
    0.14
    Activations Density 0.014%

    No Known Activations