© 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. 83158
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    otent
    -0.08
    quo
    -0.07
    frau
    -0.07
    byname
    -0.07
    ERGE
    -0.07
    lfw
    -0.07
    SharedPointer
    -0.07
    isinden
    -0.07
    ossa
    -0.07
    थ
    -0.07
    POSITIVE LOGITS
    ew
    0.08
    sgiving
    0.08
    sg
    0.08
    ably
    0.08
     prov
    0.07
    ram
    0.07
    nowled
    0.07
     adjud
    0.07
    abbo
    0.07
    ht
    0.07
    Activations Density 0.005%

    No Known Activations