© 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. 22-LLAMASCOPE-RES-131K
    11. 4073
    Prev
    Next
    INDEX
    Explanations

    configuration parameters in a file format

    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
    úi
    -0.08
    iple
    -0.08
    krom
    -0.07
    коз
    -0.07
    ulum
    -0.07
    -redux
    -0.07
    unden
    -0.07
    κ
    -0.07
     nuest
    -0.07
    andel
    -0.07
    POSITIVE LOGITS
     Bailey
    0.06
    lian
    0.06
     ru
    0.06
     half
    0.06
     when
    0.06
    ley
    0.05
     Byrne
    0.05
    è¼Ķ
    0.05
     T
    0.05
     Tob
    0.05
    Activations Density 0.006%

    No Known Activations