© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127712
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements in documents

    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
     Sisters
    -0.07
    mania
    -0.07
    ourcem
    -0.07
    agne
    -0.06
    assi
    -0.06
    rodu
    -0.06
    nict
    -0.06
    ahun
    -0.06
    ÑģÑĤÑĢÑĥ
    -0.06
    icari
    -0.06
    POSITIVE LOGITS
    ptest
    0.07
    ASA
    0.06
    >Returns
    0.06
    /apps
    0.06
    _ZONE
    0.06
    ppo
    0.06
    AccessException
    0.06
    809
    0.06
    ToProps
    0.06
    .scala
    0.06
    Activations Density 0.205%

    No Known Activations