© 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. 56514
    Prev
    Next
    INDEX
    Explanations

    references to various components or dimensions of a project or process

    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
    onga
    -0.07
     etc
    -0.07
    laden
    -0.07
    нÑİ
    -0.07
    aticon
    -0.06
    echa
    -0.06
     overall
    -0.06
    ä¸ĸ
    -0.06
    die
    -0.06
    porno
    -0.06
    POSITIVE LOGITS
     including
    0.07
    including
    0.07
    cluding
    0.07
    SI
    0.07
     INCLUDING
    0.07
    ÑĢаÑĤно
    0.07
    adal
    0.06
    ãĥ³ãĥĦ
    0.06
    viso
    0.06
    ogram
    0.06
    Activations Density 0.007%

    No Known Activations