© 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. 126940
    Prev
    Next
    INDEX
    Explanations

    prominent names or figures in various contexts

    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
    phia
    -0.08
    zioni
    -0.07
    peÄį
    -0.07
    ocre
    -0.07
    ãĤ«ãĥĨ
    -0.07
    екÑģи
    -0.07
    anian
    -0.07
    hte
    -0.07
    èo
    -0.07
    amed
    -0.07
    POSITIVE LOGITS
     therefore
    0.07
     also
    0.07
     example
    0.07
     again
    0.07
     examples
    0.07
     note
    0.06
    :
    0.06
    ?url
    0.06
     Example
    0.06
     however
    0.06
    Activations Density 0.015%

    No Known Activations