© 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. 15-LLAMASCOPE-RES-131K
    6. 27123
    Prev
    Next
    INDEX
    Explanations

    references to textual visibility and accessibility in relation to legal or copyright issues

    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
    rawer
    -0.07
    lehem
    -0.07
    ESCO
    -0.06
    ç°
    -0.06
    ouden
    -0.06
     Ngh
    -0.06
    klä
    -0.06
    ÑģÑĤв
    -0.06
    araoh
    -0.06
     å¯
    -0.06
    POSITIVE LOGITS
     hyp
    0.07
     sil
    0.07
     original
    0.07
    ero
    0.07
    customize
    0.06
    urs
    0.06
    bih
    0.06
    attery
    0.06
    ORIA
    0.06
    _td
    0.06
    Activations Density 0.002%

    No Known Activations