Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 119218
    Prev
    Next
    INDEX
    Explanations

    instructions or points of initiation

    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
    zza
    -0.07
    591
    -0.06
    abe
    -0.06
    antz
    -0.06
    rou
    -0.06
    cba
    -0.06
    ÑĨеп
    -0.06
    CHAN
    -0.06
    afx
    -0.06
    86
    -0.05
    POSITIVE LOGITS
    DOMContentLoaded
    0.07
    оÑĤоÑĢ
    0.06
    зÑĭ
    0.06
    utenberg
    0.06
    andler
    0.06
    омен
    0.06
     Pi
    0.06
     modern
    0.06
    lice
    0.06
    ulled
    0.06
    Activations Density 0.000%

    No Known Activations