© 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. 105935
    Prev
    Next
    INDEX
    Explanations

    terms related to professional roles and responsibilities across various fields

    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
    .gdx
    -0.08
    олж
    -0.07
    erties
    -0.07
     :č↵
    -0.06
    imler
    -0.06
    onder
    -0.06
    .DataTable
    -0.06
     Ferd
    -0.06
    ogan
    -0.06
     DbType
    -0.06
    POSITIVE LOGITS
    wiÄħ
    0.07
     poil
    0.07
    ég
    0.07
    /misc
    0.06
     Greene
    0.06
    åŃĿ
    0.06
     Güven
    0.06
     ظ
    0.06
    iš
    0.06
    imestep
    0.06
    Activations Density 0.086%

    No Known Activations