© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126250
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating significant pauses or separations in text

    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
    stakes
    -0.08
    ahat
    -0.07
    Increment
    -0.06
    etting
    -0.06
    arten
    -0.06
    803
    -0.06
    endum
    -0.06
    amoto
    -0.06
    AYOUT
    -0.06
     Bash
    -0.06
    POSITIVE LOGITS
    esz
    0.07
    aco
    0.07
    irie
    0.06
     Nas
    0.06
    Ŀ
    0.06
    DX
    0.06
    borough
    0.05
     Gord
    0.05
    elin
    0.05
     Bryan
    0.05
    Activations Density 0.000%

    No Known Activations