© 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. 76951
    Prev
    Next
    INDEX
    Explanations

    terms related to kidnapping and abduction

    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
     Seal
    -0.07
    ró
    -0.07
    degree
    -0.07
    rze
    -0.07
    hm
    -0.07
    анов
    -0.07
    imum
    -0.07
    estion
    -0.07
    arn
    -0.06
     Degree
    -0.06
    POSITIVE LOGITS
    ambi
    0.07
    /releases
    0.07
    ustrial
    0.07
    omain
    0.07
     kid
    0.06
    alex
    0.06
    ationally
    0.06
     abduction
    0.06
    orama
    0.06
     Linh
    0.06
    Activations Density 0.004%

    No Known Activations