© 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. 15-LLAMASCOPE-RES-131K
    6. 61874
    Prev
    Next
    INDEX
    Explanations

    discussions and analyses of procedural or policy recommendations

    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
    redients
    -0.08
    erable
    -0.07
    legen
    -0.07
    marvin
    -0.07
     ì¡°êµIJ
    -0.07
    oods
    -0.07
    UPPORT
    -0.07
    REDIENT
    -0.07
    vertime
    -0.07
     lô
    -0.07
    POSITIVE LOGITS
     some
    0.09
     also
    0.07
     disp
    0.07
     other
    0.07
     append
    0.07
     how
    0.06
     touch
    0.06
     tips
    0.06
     examples
    0.06
     exclusive
    0.06
    Activations Density 0.030%

    No Known Activations