Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126632
    Prev
    Next
    INDEX
    Explanations

    instances of the verbs "have" and "has," particularly in relation to discussions involving experiences or occurrences

    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
    uli
    -0.10
    ulos
    -0.07
    adlo
    -0.07
    ÏĦαÏĤ
    -0.07
    ाध
    -0.07
    still
    -0.07
    adia
    -0.07
     verze
    -0.07
    ngth
    -0.07
    kel
    -0.07
    POSITIVE LOGITS
     lately
    0.07
     since
    0.07
    emi
    0.06
    lore
    0.06
    OwnProperty
    0.06
    dfa
    0.06
    ipar
    0.06
    åĮ
    0.06
    htags
    0.06
    .osgi
    0.06
    Activations Density 0.004%

    No Known Activations