© 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. 40582
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and events

    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
    antino
    -0.09
    chner
    -0.07
    Äįka
    -0.07
    Ñĥки
    -0.07
    abler
    -0.07
    WithValue
    -0.07
    andro
    -0.07
    uide
    -0.07
    å»·
    -0.07
    loquent
    -0.07
    POSITIVE LOGITS
     claim
    0.09
     believes
    0.08
     convinced
    0.08
     believe
    0.08
     claims
    0.08
    认为
    0.08
     saying
    0.07
     belief
    0.07
     view
    0.07
     said
    0.07
    Activations Density 0.033%

    No Known Activations