© 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. 15-LLAMASCOPE-RES-131K
    11. 103575
    Prev
    Next
    INDEX
    Explanations

    phrases indicating awards or recognition

    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
    ìķ¤
    -0.07
    tam
    -0.06
    DAQ
    -0.06
    awning
    -0.05
    poon
    -0.05
     Attach
    -0.05
    jon
    -0.05
    _SECTION
    -0.05
    onestly
    -0.05
     Mim
    -0.05
    POSITIVE LOGITS
    201
    0.11
    202
    0.11
    963
    0.08
    dech
    0.07
    200
    0.07
    isch
    0.07
    rvine
    0.07
     nÄĥm
    0.07
     gezocht
    0.07
    -redux
    0.07
    Activations Density 0.022%

    No Known Activations