© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89804
    Prev
    Next
    INDEX
    Explanations

    words indicating inclusivity or generality

    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
    akk
    -0.06
     Stra
    -0.06
    ï¸
    -0.06
    oref
    -0.06
    wang
    -0.06
    eway
    -0.06
     regards
    -0.05
    ked
    -0.05
    eÄį
    -0.05
    :bg
    -0.05
    POSITIVE LOGITS
     other
    0.25
    other
    0.20
    åħ¶ä»ĸ
    0.19
     autres
    0.18
    .other
    0.17
    -other
    0.17
    _other
    0.16
     otros
    0.16
     altri
    0.16
    (other
    0.16
    Activations Density 0.021%

    No Known Activations