© 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. 22-LLAMASCOPE-RES-131K
    11. 4181
    Prev
    Next
    INDEX
    Explanations

    references to font styles and attributes in text

    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
    geh
    -0.07
    Ùĥ
    -0.07
    oly
    -0.07
    thic
    -0.07
    oa
    -0.06
     ruling
    -0.06
    utr
    -0.06
    _Generic
    -0.06
    usterity
    -0.06
    оÑĢÑĤÑĥ
    -0.06
    POSITIVE LOGITS
    aine
    0.10
    _HERSHEY
    0.09
    echa
    0.08
    .googleapis
    0.08
    astic
    0.08
    .gstatic
    0.08
    structions
    0.07
     Howell
    0.07
    ijn
    0.07
    aines
    0.07
    Activations Density 0.002%

    No Known Activations