© 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. 17-LLAMASCOPE-RES-131K
    6. 75267
    Prev
    Next
    INDEX
    Explanations

    words indicating conditions, definitions, and relationships in a technical 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
    971
    -0.06
    ष
    -0.06
    fish
    -0.06
    leon
    -0.06
    Ì
    -0.06
    _tpl
    -0.06
    .scalablytyped
    -0.06
     Dungeons
    -0.05
    516
    -0.05
    ãĥ³ãĥĹ
    -0.05
    POSITIVE LOGITS
     tower
    0.09
     towers
    0.08
     Tower
    0.07
     mast
    0.07
    kke
    0.07
     site
    0.07
    Äĥr
    0.07
    år
    0.07
     Towers
    0.07
     coloc
    0.07
    Activations Density 0.000%

    No Known Activations