© 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. 129043
    Prev
    Next
    INDEX
    Explanations

    references to media outlets and 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
    ivé
    -0.07
    Ñľ
    -0.06
     dis
    -0.05
    gone
    -0.05
    ther
    -0.05
     publicly
    -0.05
    owie
    -0.05
    ог
    -0.05
    uw
    -0.05
     Franco
    -0.05
    POSITIVE LOGITS
    μÏīÏĤ
    0.08
    ormsg
    0.07
     GmbH
    0.07
    aylight
    0.07
    idenav
    0.07
    ï¼Ĭ
    0.07
    ises
    0.07
     Españ
    0.07
     olsun
    0.07
    ÑģÑĤа
    0.06
    Activations Density 0.180%

    No Known Activations