© 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. 126852
    Prev
    Next
    INDEX
    Explanations

    references to initial points of discussion or analysis

    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
    ings
    -0.08
     ing
    -0.08
    oe
    -0.07
     Ing
    -0.06
    ady
    -0.06
    anzi
    -0.06
    Äĥn
    -0.06
    staking
    -0.06
    778
    -0.06
     Dân
    -0.06
    POSITIVE LOGITS
    REDIENT
    0.07
     point
    0.07
    iator
    0.07
     åĥ
    0.07
    iat
    0.07
    -point
    0.07
    gist
    0.07
    conditions
    0.06
    auss
    0.06
    rek
    0.06
    Activations Density 0.007%

    No Known Activations