© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85723
    Prev
    Next
    INDEX
    Explanations

    names or titles of individuals associated with intense or significant actions or roles

    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
    .Dictionary
    -0.07
     ifndef
    -0.07
     клад
    -0.07
    975
    -0.07
    .GetObject
    -0.07
    кÑĥлÑı
    -0.06
    quina
    -0.06
     Schwartz
    -0.06
     xuyên
    -0.06
     enumerator
    -0.06
    POSITIVE LOGITS
    ábado
    0.09
    ondo
    0.08
    .mybatisplus
    0.06
     Vanguard
    0.06
    ibraries
    0.06
    jur
    0.06
    cedure
    0.06
    HIR
    0.06
    roach
    0.06
    eye
    0.06
    Activations Density 0.000%

    No Known Activations