© 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. 31-LLAMASCOPE-RES-32K
    11. 7005
    Prev
    Next
    INDEX
    Explanations

    specific elements or identifiers related to music, particularly in various formats or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     X
    -0.14
    .tbl
    -0.12
     Xu
    -0.12
    lrt
    -0.12
    bp
    -0.12
    DataManager
    -0.12
    elters
    -0.12
    ,X
    -0.12
    bmp
    -0.11
    idd
    -0.11
    POSITIVE LOGITS
    z
    1.05
    ze
    0.77
    zes
    0.73
    za
    0.73
    zi
    0.72
    zy
    0.71
    zb
    0.70
    zM
    0.70
    zt
    0.69
    zo
    0.69
    Activations Density 0.184%

    No Known Activations