© 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. 29739
    Prev
    Next
    INDEX
    Explanations

    terms related to infection and transformation into zombie-like states

    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
     Sanat
    -0.10
    arrass
    -0.08
    incerely
    -0.08
    éŁ¿
    -0.08
    ÑĢиÑģÑĤи
    -0.07
    uppy
    -0.07
    ocu
    -0.07
    alah
    -0.07
    ozÃŃ
    -0.07
    tings
    -0.07
    POSITIVE LOGITS
     transform
    0.07
     transformation
    0.06
     become
    0.06
     transforming
    0.06
     becoming
    0.06
     transformations
    0.06
     transformed
    0.06
    -controls
    0.06
     control
    0.06
     converting
    0.06
    Activations Density 0.014%

    No Known Activations