© 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. 118978
    Prev
    Next
    INDEX
    Explanations

    dialogue and quotes in the text

    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
    lesen
    -0.08
    ynth
    -0.08
    COND
    -0.07
    alsa
    -0.07
    ammers
    -0.07
    acus
    -0.07
    doch
    -0.07
     Bridges
    -0.07
    alu
    -0.07
    ãģĵãģĨ
    -0.07
    POSITIVE LOGITS
     referring
    0.16
     refer
    0.14
     reference
    0.13
     refers
    0.13
     referencing
    0.11
     references
    0.10
     Refer
    0.10
    refer
    0.10
     referencia
    0.10
     referred
    0.09
    Activations Density 0.009%

    No Known Activations