Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16559
    Prev
    Next
    INDEX
    Explanations

    terminology related to species classification and biological taxonomy

    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
    lix
    -0.07
    ennie
    -0.06
     Cons
    -0.06
     Erg
    -0.06
     Examiner
    -0.06
    lsen
    -0.06
     revel
    -0.05
    word
    -0.05
    pest
    -0.05
    TED
    -0.05
    POSITIVE LOGITS
    /Branch
    0.07
    atron
    0.07
    ereotype
    0.07
    алÑĸв
    0.07
    .Branch
    0.07
    tÃŃ
    0.07
    .dirty
    0.07
    baum
    0.07
    APT
    0.07
     Dust
    0.06
    Activations Density 0.001%

    No Known Activations