© 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. 83236
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used in various contexts

    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
    пÑĢиклад
    -0.09
    icl
    -0.08
    avra
    -0.06
    esson
    -0.06
    ponge
    -0.06
    ts
    -0.06
    aviors
    -0.06
    .oauth
    -0.06
     sorts
    -0.06
    earable
    -0.06
    POSITIVE LOGITS
    álo
    0.07
    rame
    0.07
     note
    0.07
     Vander
    0.06
    923
    0.06
    omas
    0.06
    omic
    0.06
     rightly
    0.06
    agner
    0.06
    loon
    0.06
    Activations Density 0.018%

    No Known Activations