© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 62424
    Prev
    Next
    INDEX
    Explanations

    specific identifiers, references, or markers in an academic context

    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
    209
    -0.06
    â̦↵
    -0.05
    era
    -0.05
     Katz
    -0.05
    ¯
    -0.05
    ...↵
    -0.05
     alloc
    -0.05
     di
    -0.05
     Moon
    -0.05
    ullet
    -0.05
    POSITIVE LOGITS
    .fig
    0.09
    Ngh
    0.08
    ixo
    0.08
    lech
    0.08
    contres
    0.07
    lse
    0.07
     ydk
    0.07
    Fcn
    0.07
    .LA
    0.07
    _exempt
    0.07
    Activations Density 0.000%

    No Known Activations