© 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. 28878
    Prev
    Next
    INDEX
    Explanations

    references to scoring, points, and rewards

    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
    olle
    -0.07
    INO
    -0.07
     Beam
    -0.07
    mlin
    -0.06
    inkle
    -0.06
    Ñħодим
    -0.06
    _singleton
    -0.06
    oksen
    -0.06
    ç«ĭãģ¦
    -0.06
    	Destroy
    -0.06
    POSITIVE LOGITS
    PerPixel
    0.07
    loss
    0.07
     Laud
    0.07
    -valu
    0.06
    cheme
    0.06
     Kro
    0.06
     bagi
    0.06
     LOSS
    0.06
    atest
    0.06
    erez
    0.06
    Activations Density 0.021%

    No Known Activations