© 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. 6491
    Prev
    Next
    INDEX
    Explanations

    affirmations or acknowledgments of agreement

    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
    _ASSUME
    -0.18
    nici
    -0.16
    strup
    -0.15
    owler
    -0.14
    à¹ĥà¸Ķ
    -0.14
    Ñģом
    -0.14
    uentes
    -0.14
    olvers
    -0.14
    欲
    -0.14
    uffles
    -0.14
    POSITIVE LOGITS
    AY
    0.34
     fine
    0.33
    ay
    0.31
    lahoma
    0.29
    ays
    0.29
    tober
    0.27
    fine
    0.25
     Fine
    0.25
     then
    0.23
     so
    0.23
    Activations Density 0.030%

    No Known Activations