© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 907
    Prev
    Next
    INDEX
    Explanations

    terms related to musical composition and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idente
    -0.18
    ruba
    -0.18
    kova
    -0.17
    eya
    -0.16
    stants
    -0.16
    eniable
    -0.16
     homem
    -0.16
    ocaly
    -0.15
    iciente
    -0.15
    ardo
    -0.15
    POSITIVE LOGITS
     recipient
    0.18
     неболÑĮ
    0.16
     exponent
    0.16
     mism
    0.16
     alt
    0.16
    idos
    0.16
    Ĥæķ°
    0.15
     grandes
    0.15
     blanc
    0.15
     ingredient
    0.15
    Activations Density 0.059%

    No Known Activations