Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77154
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers, such as names of people or 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
    -Se
    -0.06
    udi
    -0.06
     aut
    -0.06
    Ñģм
    -0.06
     Modern
    -0.06
    ÃŃte
    -0.06
     æ¾
    -0.06
    _HERSHEY
    -0.06
    èĪĮ
    -0.06
    znik
    -0.06
    POSITIVE LOGITS
     dün
    0.06
    isu
    0.06
    odb
    0.06
    iflower
    0.06
    angu
    0.06
    tas
    0.06
    abez
    0.06
    iso
    0.06
    Iso
    0.06
    .release
    0.06
    Activations Density 0.000%

    No Known Activations