© 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. 17-LLAMASCOPE-RES-131K
    11. 78770
    Prev
    Next
    INDEX
    Explanations

    phrases associated with social dynamics and group participation

    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
     aval
    -0.06
     scaled
    -0.06
     District
    -0.06
    ng
    -0.06
     prone
    -0.06
    arts
    -0.05
    ìľ¤
    -0.05
     observ
    -0.05
    ICI
    -0.05
     Copyright
    -0.05
    POSITIVE LOGITS
    çIJĨ
    0.07
    éal
    0.07
    Brush
    0.07
    weg
    0.06
    ansson
    0.06
     scrim
    0.06
    badge
    0.06
    ondere
    0.06
     necessity
    0.06
    eway
    0.06
    Activations Density 0.033%

    No Known Activations