© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128678
    Prev
    Next
    INDEX
    Explanations

    instances of allegations and claims involving sexual 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
    icher
    -0.08
    mess
    -0.08
    íĥ
    -0.08
    æ³ķéĻ¢
    -0.07
    iddet
    -0.07
    arakter
    -0.07
    .bid
    -0.07
    fos
    -0.07
    Ñĥва
    -0.07
     æ©
    -0.07
    POSITIVE LOGITS
    uppen
    0.06
    orn
    0.06
    867
    0.06
     Woo
    0.06
    lob
    0.06
     vign
    0.06
     bul
    0.06
     saw
    0.06
    etal
    0.06
     tut
    0.05
    Activations Density 0.023%

    No Known Activations