© 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. 82516
    Prev
    Next
    INDEX
    Explanations

    years mentioned in a chronological context

    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
    DDS
    -0.06
    CCI
    -0.06
     Stem
    -0.06
    INESS
    -0.06
    eki
    -0.06
    354
    -0.05
    610
    -0.05
    619
    -0.05
    356
    -0.05
    è³
    -0.05
    POSITIVE LOGITS
    umnos
    0.07
    راÙĩ
    0.07
     addCriterion
    0.07
    rail
    0.07
     Ñģек
    0.06
    .nc
    0.06
    tery
    0.06
     Lum
    0.06
    ainment
    0.06
    νοÏį
    0.06
    Activations Density 0.001%

    No Known Activations