© 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. 125399
    Prev
    Next
    INDEX
    Explanations

    positive feedback and evaluations regarding professional services

    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
    /OR
    -0.09
    lessly
    -0.09
    бÑĥдÑĮ
    -0.09
    perature
    -0.08
    .au
    -0.08
    ELY
    -0.08
    vý
    -0.08
    RuleContext
    -0.07
    ablish
    -0.07
    otto
    -0.07
    POSITIVE LOGITS
    âĢ¦↵↵↵
    0.09
    .Dev
    0.06
    RITE
    0.06
    олеÑĤ
    0.06
    iry
    0.06
    .timeScale
    0.05
    ForObject
    0.05
    edenÃŃ
    0.05
    лев
    0.05
     unl
    0.05
    Activations Density 2.533%

    No Known Activations