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. 9-LLAMASCOPE-RES-131K
    6. 95653
    Prev
    Next
    INDEX
    Explanations

    content related to crime and violence

    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
    DU
    -0.06
     positional
    -0.06
     sunk
    -0.06
     Arnold
    -0.06
    anio
    -0.06
     bulld
    -0.06
    bare
    -0.06
    innen
    -0.06
     trunc
    -0.06
    lear
    -0.06
    POSITIVE LOGITS
    wing
    0.07
    ignKey
    0.07
    okrat
    0.07
    ingle
    0.07
    ape
    0.07
    anken
    0.07
    éric
    0.07
    ãĥªãĥ¼ãĤº
    0.07
    ipse
    0.07
    λμ
    0.07
    Activations Density 0.000%

    No Known Activations