© 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. 26857
    Prev
    Next
    INDEX
    Explanations

    terms related to ownership and title transfer

    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
    opot
    -0.07
     Threat
    -0.07
    archs
    -0.07
    sealed
    -0.07
    $MESS
    -0.07
    wind
    -0.07
    llu
    -0.06
     \`
    -0.06
    ıcı
    -0.06
    ording
    -0.06
    POSITIVE LOGITS
     quant
    0.07
     isAuthenticated
    0.06
    UBLE
    0.06
     çī©
    0.06
    Chan
    0.06
     اÙĦاØŃ
    0.06
     coll
    0.06
    PCA
    0.06
     Quant
    0.05
    OU
    0.05
    Activations Density 0.001%

    No Known Activations