© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125789
    Prev
    Next
    INDEX
    Explanations

    contact information and data related to organizations or individuals

    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
     recommendation
    -0.06
    å·
    -0.06
    alten
    -0.06
    iously
    -0.06
    ayar
    -0.06
    oni
    -0.06
    ledi
    -0.06
    bindung
    -0.06
    closure
    -0.05
    esi
    -0.05
    POSITIVE LOGITS
    /goto
    0.07
    .AttributeSet
    0.06
     Conc
    0.06
    PIO
    0.06
    본
    0.06
    HUD
    0.06
    ÑģÑĮк
    0.06
     Te
    0.06
    verity
    0.06
    /chart
    0.06
    Activations Density 0.010%

    No Known Activations