© 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. 55796
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting community and support for individuals

    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
    olia
    -0.07
    úc
    -0.07
    oret
    -0.07
    олом
    -0.07
     PROCUREMENT
    -0.07
    ory
    -0.07
    .sendFile
    -0.07
    inia
    -0.07
    buch
    -0.07
    ãĥªãĤ«
    -0.07
    POSITIVE LOGITS
     mission
    0.07
    ment
    0.07
     cause
    0.07
    iquid
    0.06
     communities
    0.06
     Cause
    0.06
    pace
    0.06
    ivet
    0.06
    ------+------+
    0.06
     development
    0.06
    Activations Density 0.037%

    No Known Activations