© 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. 83124
    Prev
    Next
    INDEX
    Explanations

    words that categorize ideological associations or movements related to identity and belief

    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
    eyse
    -0.07
    oggle
    -0.07
    angent
    -0.06
    oret
    -0.06
    Ìī
    -0.06
     kê
    -0.06
    rz
    -0.06
    ibo
    -0.06
     ach
    -0.06
    bk
    -0.06
    POSITIVE LOGITS
     similarly
    0.09
     váºŃy
    0.07
    andom
    0.07
    antan
    0.07
    ç«
    0.07
     Similarly
    0.07
     earlier
    0.06
     theirs
    0.06
     predecessors
    0.06
    920
    0.06
    Activations Density 0.035%

    No Known Activations