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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95521
    Prev
    Next
    INDEX
    Explanations

    names of politicians and their affiliations

    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
    urr
    -0.07
    hung
    -0.07
    bsites
    -0.07
    lift
    -0.06
    prix
    -0.06
    ÑĢÑıдÑĥ
    -0.06
    tober
    -0.06
    sembl
    -0.06
    ÑĮе
    -0.06
    SA
    -0.06
    POSITIVE LOGITS
     è±
    0.06
    iyle
    0.06
    ãĤĪãģĨ
    0.06
     rall
    0.06
    èģ
    0.06
     Cann
    0.06
    컵
    0.06
     Vill
    0.06
    -y
    0.06
    mayan
    0.06
    Activations Density 0.036%

    No Known Activations