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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5209
    Prev
    Next
    INDEX
    Explanations

    language used to express expectations and conditions in formal or legal contexts

    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
    зи
    -0.06
    çĥ
    -0.06
    yo
    -0.06
    obraz
    -0.06
    acus
    -0.06
     Telephone
    -0.06
    ottes
    -0.06
    ob
    -0.06
    readcr
    -0.06
    ooks
    -0.06
    POSITIVE LOGITS
    orph
    0.07
    ittal
    0.07
    uar
    0.06
    ital
    0.06
     expressions
    0.06
     negate
    0.06
     cover
    0.06
    NECT
    0.06
    ango
    0.06
    аÑģÑĤ
    0.06
    Activations Density 0.002%

    No Known Activations