© 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. 106855
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quantity or identification of individuals within a group

    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
    ABCDEFGHI
    -0.09
    oul
    -0.08
    _VC
    -0.07
    ohana
    -0.07
    .scalablytyped
    -0.06
    ABCDEFG
    -0.06
    हर
    -0.06
    äºŃ
    -0.06
    ứ
    -0.06
     ãĢij
    -0.06
    POSITIVE LOGITS
     those
    0.10
    those
    0.08
     Those
    0.08
     ones
    0.07
    Those
    0.07
     statistics
    0.07
     Anonymous
    0.07
     anonymous
    0.07
     Spar
    0.06
     tersebut
    0.06
    Activations Density 0.013%

    No Known Activations