© 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. 118501
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its internal classifications or comments on governmental strategies

    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
    isches
    -0.08
    ëĤĺëĿ¼
    -0.07
    RET
    -0.06
     ALS
    -0.06
    Ïģια
    -0.06
    èĨ
    -0.06
     Chief
    -0.06
     SEL
    -0.06
     Roe
    -0.06
     Dit
    -0.06
    POSITIVE LOGITS
    ehler
    0.07
     Güven
    0.07
    ähr
    0.07
    uncios
    0.07
    üven
    0.07
    ÙĪÙĦÙĬ
    0.07
    onymous
    0.07
    ehr
    0.06
    IVER
    0.06
    ignet
    0.06
    Activations Density 0.005%

    No Known Activations