© 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. 16145
    Prev
    Next
    INDEX
    Explanations

    legal terms related to petitioners and respondents in 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
    rary
    -0.08
    oth
    -0.07
    Ñıб
    -0.07
    TAIL
    -0.07
    ite
    -0.07
     kalp
    -0.06
    vet
    -0.06
    εÏģÏĮ
    -0.06
    åŀ
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
    /comment
    0.06
     vs
    0.06
     èŃ
    0.06
     versus
    0.06
    åĬ¡
    0.06
    _firestore
    0.06
     PIXI
    0.05
    _vs
    0.05
    UNUSED
    0.05
     RequestOptions
    0.05
    Activations Density 0.004%

    No Known Activations