© 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. 125277
    Prev
    Next
    INDEX
    Explanations

    activities or initiatives related to community support and charitable actions

    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
    bose
    -0.09
    ongan
    -0.07
    trak
    -0.07
    anko
    -0.07
    otate
    -0.06
    _DEAD
    -0.06
    оÑĤ
    -0.06
     Gä
    -0.06
     localVar
    -0.06
     ков
    -0.06
    POSITIVE LOGITS
    irl
    0.06
    eral
    0.06
     thousands
    0.06
     Project
    0.06
     bore
    0.06
    thal
    0.05
     scholarships
    0.05
    lr
    0.05
     musical
    0.05
    sch
    0.05
    Activations Density 0.045%

    No Known Activations