© 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. 93678
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "name" and its variations

    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
    еÑĢеж
    -0.07
    esson
    -0.07
    .subscriptions
    -0.06
    948
    -0.06
    еÑĢк
    -0.06
    -fly
    -0.06
    _via
    -0.06
    .qq
    -0.06
    Deck
    -0.06
    olie
    -0.06
    POSITIVE LOGITS
    plate
    0.08
    plates
    0.07
    geber
    0.07
    ake
    0.07
    /title
    0.07
     sake
    0.06
     CallingConvention
    0.06
    284
    0.06
    bable
    0.06
    749
    0.06
    Activations Density 0.009%

    No Known Activations