© 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. 28745
    Prev
    Next
    INDEX
    Explanations

    references to companionship and guardianship

    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
    odd
    -0.08
    pla
    -0.07
    _VIRTUAL
    -0.07
    ór
    -0.07
    _DISPATCH
    -0.07
    roj
    -0.06
    è§
    -0.06
    ToDevice
    -0.06
    StateManager
    -0.06
    gable
    -0.06
    POSITIVE LOGITS
    914
    0.06
     pard
    0.06
    rag
    0.06
    usercontent
    0.06
    決
    0.06
    ÇIJ
    0.06
    ÑĢана
    0.06
    utt
    0.06
     Canter
    0.05
     overst
    0.05
    Activations Density 0.036%

    No Known Activations