© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77423
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to web or server-side programming

    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
    work
    -0.06
    ÙĦاÙħ
    -0.06
    annes
    -0.05
    PELL
    -0.05
    zu
    -0.05
    635
    -0.05
    ongyang
    -0.05
    .cms
    -0.05
    wan
    -0.05
    vl
    -0.05
    POSITIVE LOGITS
    çĽĬ
    0.07
    storybook
    0.07
    infeld
    0.07
     елекÑĤÑĢон
    0.07
     Plantae
    0.07
     елек
    0.07
    \/\/
    0.06
    tz
    0.06
    bst
    0.06
    smarty
    0.06
    Activations Density 0.000%

    No Known Activations