© 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. 61128
    Prev
    Next
    INDEX
    Explanations

    references to media organizations and press-related entities

    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
    лев
    -0.07
    rael
    -0.06
     Weinstein
    -0.06
    juven
    -0.06
     termin
    -0.06
     Pruitt
    -0.06
    ouver
    -0.06
    Č↵
    -0.06
    ubber
    -0.06
     and
    -0.06
    POSITIVE LOGITS
    iero
    0.06
    aticon
    0.06
     "(\<
    0.06
    ouz
    0.06
     hã
    0.06
    agli
    0.06
    ROADCAST
    0.06
    عÙĨ
    0.06
     تÙĦ
    0.06
    chine
    0.06
    Activations Density 0.015%

    No Known Activations