© 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. 128967
    Prev
    Next
    INDEX
    Explanations

    references to New Hampshire and associated health topics

    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
    eza
    -0.07
    ar
    -0.06
    and
    -0.06
    EVER
    -0.06
    e
    -0.06
    an
    -0.06
    andal
    -0.06
    ereotype
    -0.06
    erer
    -0.06
    raft
    -0.06
    POSITIVE LOGITS
    irsch
    0.09
    azz
    0.09
    tru
    0.08
    ira
    0.07
    ase
    0.07
    ضÙħ
    0.07
    illy
    0.07
    ales
    0.07
    antal
    0.07
    RA
    0.07
    Activations Density 0.034%

    No Known Activations