© 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. 5-LLAMASCOPE-RES-131K
    11. 126437
    Prev
    Next
    INDEX
    Explanations

    references to internal conflict and the desire for belonging or acceptance

    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
    atform
    -0.08
    enticator
    -0.07
     Trad
    -0.07
    riterion
    -0.07
    ovit
    -0.07
    addy
    -0.06
     dụ
    -0.06
    unal
    -0.06
    ater
    -0.06
    ãģ»ãģ©
    -0.06
    POSITIVE LOGITS
    FAULT
    0.07
    OperationException
    0.06
    dorf
    0.06
    invoke
    0.06
    ContentSize
    0.06
     sıkıntı
    0.06
    ropa
    0.06
    prefix
    0.05
     Prefix
    0.05
     extortion
    0.05
    Activations Density 0.159%

    No Known Activations