© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs, particularly those expressing intention or purpose

    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
    sworth
    -0.07
    ãĤ¤ãĥī
    -0.07
     Baum
    -0.07
    ead
    -0.07
    edes
    -0.07
    odus
    -0.06
    loh
    -0.06
    assis
    -0.06
    lfw
    -0.06
    /Area
    -0.06
    POSITIVE LOGITS
     happening
    0.07
    coma
    0.07
     bare
    0.06
    ÑĢоÑĤ
    0.06
    igator
    0.06
    keh
    0.06
    owej
    0.06
    elen
    0.06
     happen
    0.06
     eventual
    0.06
    Activations Density 0.028%

    No Known Activations