© 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. 82762
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and administrative processes concerning immigration

    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
    immer
    -0.07
    empt
    -0.06
    iento
    -0.06
    ookies
    -0.06
    Äħd
    -0.06
     Stateless
    -0.06
    zew
    -0.06
     ditch
    -0.06
    ellan
    -0.06
    otti
    -0.06
    POSITIVE LOGITS
    leigh
    0.07
    tol
    0.07
    _VOID
    0.06
    703
    0.06
    ë²Ħì§Ģ
    0.06
    ardo
    0.06
    imson
    0.06
    ney
    0.06
    ILING
    0.06
    706
    0.06
    Activations Density 0.000%

    No Known Activations