© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95574
    Prev
    Next
    INDEX
    Explanations

    terms associated with social issues and community-related challenges

    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
    acher
    -0.07
    ach
    -0.06
    agt
    -0.06
    phet
    -0.06
    licht
    -0.06
    rix
    -0.06
    ane
    -0.06
    cci
    -0.06
     Bottom
    -0.05
    bb
    -0.05
    POSITIVE LOGITS
     mastur
    0.10
    .scalablytyped
    0.08
    .xmlbeans
    0.08
    надлеж
    0.08
     excer
    0.07
    suppress
    0.07
    __,__
    0.07
    fea
    0.07
    ÛĮزÛĮ
    0.07
    _keeper
    0.07
    Activations Density 0.049%

    No Known Activations