© 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. 9-LLAMASCOPE-RES-131K
    11. 95500
    Prev
    Next
    INDEX
    Explanations

    references to specific radio stations or media outlets

    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
    ixo
    -0.09
    NavItem
    -0.08
    éĭ
    -0.07
    IBE
    -0.07
    quals
    -0.07
    ãģªãģĮ
    -0.07
    ÑĢави
    -0.07
    vero
    -0.07
    orra
    -0.07
    chants
    -0.07
    POSITIVE LOGITS
    eral
    0.06
    ac
    0.06
    onz
    0.06
    a
    0.06
    ce
    0.06
    orm
    0.06
    erie
    0.05
     immune
    0.05
    etail
    0.05
    eday
    0.05
    Activations Density 0.001%

    No Known Activations