© 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. 125986
    Prev
    Next
    INDEX
    Explanations

    structured programming or coding syntax elements

    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
     Mahar
    -0.08
    ãĥ¼ãĥĢ
    -0.08
    νον
    -0.07
    .rs
    -0.07
    jspx
    -0.07
    èį
    -0.07
    icari
    -0.07
    Sharper
    -0.07
    Ïĥκε
    -0.07
    ì§
    -0.07
    POSITIVE LOGITS
    thing
    0.06
    vice
    0.06
    altung
    0.06
    andel
    0.06
    asco
    0.06
     Mans
    0.05
    robe
    0.05
    alles
    0.05
    anky
    0.05
     canopy
    0.05
    Activations Density 1.032%

    No Known Activations