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. 82963
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and court activities

    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
    -metadata
    -0.06
    áli
    -0.06
    urd
    -0.06
    credited
    -0.06
    coop
    -0.06
    meteor
    -0.06
     repealed
    -0.06
    emploi
    -0.06
     Snape
    -0.05
     goof
    -0.05
    POSITIVE LOGITS
    daf
    0.08
     hearing
    0.07
    ibr
    0.07
    idebar
    0.07
     scheduling
    0.07
    imas
    0.06
     motions
    0.06
     à¤ħà¤Ĺल
    0.06
    amac
    0.06
    bind
    0.06
    Activations Density 0.011%

    No Known Activations