© 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. 5-LLAMASCOPE-RES-131K
    11. 126411
    Prev
    Next
    INDEX
    Explanations

    notable historical figures and organizations

    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
    nite
    -0.07
    baugh
    -0.06
    çĴĥ
    -0.06
    ecies
    -0.06
    xit
    -0.06
    403
    -0.06
    annes
    -0.06
    flo
    -0.06
    eos
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
    _nullable
    0.06
    isko
    0.06
    akis
    0.06
    @m
    0.06
    oya
    0.06
    iri
    0.06
    irk
    0.06
    mith
    0.06
    İ
    0.06
    inger
    0.06
    Activations Density 0.001%

    No Known Activations