© 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. 40235
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate presence or association with a person, object, or concept

    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
    áng
    -0.07
    άκ
    -0.07
    arkin
    -0.07
     ImmutableList
    -0.07
    ÂĿ
    -0.06
    mbH
    -0.06
     Frequently
    -0.06
    ırak
    -0.06
    :↵↵↵↵↵↵
    -0.06
    Ãły
    -0.06
    POSITIVE LOGITS
     further
    0.08
     exception
    0.08
     others
    0.08
     also
    0.08
     exceptions
    0.07
    ps
    0.07
     no
    0.07
    ktion
    0.07
     corresponding
    0.07
     perhaps
    0.07
    Activations Density 0.045%

    No Known Activations