© 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. 17-LLAMASCOPE-RES-131K
    11. 74821
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by" related to authorship or credit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.08
    éĺħ读次æķ°
    -0.08
    fak
    -0.08
    PathParam
    -0.07
    tember
    -0.07
    vÄĽt
    -0.07
    $I
    -0.07
    THR
    -0.07
    omik
    -0.07
    ầ
    -0.07
    POSITIVE LOGITS
     Crowley
    0.07
    oure
    0.07
    /on
    0.07
    :
    0.06
    uv
    0.06
    888
    0.06
    ìŀĶ
    0.06
     quint
    0.06
     E
    0.06
     Brow
    0.06
    Activations Density 0.003%

    No Known Activations