© 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. 55978
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidance or instructions on actions to take

    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
    Interop
    -0.07
     Ãĸzel
    -0.07
    ìĭ¸
    -0.06
    çak
    -0.06
    NodeId
    -0.06
    _Object
    -0.06
    .onViewCreated
    -0.06
    ÅĽcie
    -0.06
     indef
    -0.06
    _Api
    -0.06
    POSITIVE LOGITS
    aves
    0.08
    .liferay
    0.08
    ges
    0.07
    .JPG
    0.07
    ?↵
    0.07
     nutshell
    0.07
    /Public
    0.07
    rek
    0.07
    umont
    0.07
    urai
    0.06
    Activations Density 0.294%

    No Known Activations