© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation or commendation

    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
    D
    -0.07
    isc
    -0.06
     Bradford
    -0.06
    du
    -0.06
     Duch
    -0.05
    ing
    -0.05
     Boyle
    -0.05
    EMA
    -0.05
    owski
    -0.05
    utta
    -0.05
    POSITIVE LOGITS
    éĢ¸
    0.08
    å¼¥
    0.08
    Insensitive
    0.07
     ç±
    0.07
    μον
    0.07
     å¾Ĵ
    0.07
     Admin
    0.07
    ProcessEvent
    0.07
    INLINE
    0.07
    _asm
    0.07
    Activations Density 0.032%

    No Known Activations