© 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. 40581
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and."

    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
     also
    -0.08
     ALSO
    -0.07
    PLUS
    -0.06
    also
    -0.06
     other
    -0.06
    Also
    -0.06
     Also
    -0.06
    uš
    -0.06
     juga
    -0.06
    icens
    -0.06
    POSITIVE LOGITS
    this
    0.07
    although
    0.07
    869
    0.07
    621
    0.07
    604
    0.07
     although
    0.06
    though
    0.06
    769
    0.06
    there
    0.06
    èĻ½çĦ¶
    0.06
    Activations Density 0.039%

    No Known Activations