© 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. 90185
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and contextual markers in scientific research

    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
    Ìī
    -0.08
     print
    -0.06
    à¤Ĥपर
    -0.05
    Topics
    -0.05
     Griff
    -0.05
     occup
    -0.05
    itals
    -0.05
     meaning
    -0.05
     en
    -0.05
    @$
    -0.05
    POSITIVE LOGITS
    ắc
    0.07
    acco
    0.07
    (forKey
    0.07
    ãĥ¼ãĥĢ
    0.07
    illes
    0.07
    abbo
    0.07
    dera
    0.07
    -eslint
    0.07
    orts
    0.07
    ild
    0.07
    Activations Density 0.004%

    No Known Activations