Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29027
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate application or relevance to various contexts

    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
     appearances
    -0.07
    atti
    -0.07
     tay
    -0.07
    »
    -0.06
    adding
    -0.06
    лоÑĤ
    -0.06
     hell
    -0.06
    ates
    -0.06
    $http
    -0.06
    uario
    -0.06
    POSITIVE LOGITS
     situations
    0.09
     situation
    0.07
    ERSIST
    0.07
    ichick
    0.07
    /xhtml
    0.07
    endra
    0.07
    proc
    0.07
    zc
    0.07
     scenarios
    0.06
    PasswordField
    0.06
    Activations Density 0.019%

    No Known Activations