© 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. 5-LLAMASCOPE-RES-131K
    6. 125945
    Prev
    Next
    INDEX
    Explanations

    phrases that mention "formula" in various contexts

    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
    rog
    -0.06
     Ary
    -0.06
     view
    -0.06
     Inf
    -0.06
    point
    -0.06
    endencies
    -0.06
    fi
    -0.06
    burn
    -0.06
     whole
    -0.06
    ija
    -0.06
    POSITIVE LOGITS
    oeff
    0.09
    ingleton
    0.08
    erule
    0.08
    ì¹Ļ
    0.07
     ConnectionState
    0.07
    aland
    0.07
    miner
    0.07
    ³
    0.07
    PEND
    0.07
    ±
    0.07
    Activations Density 0.010%

    No Known Activations