© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87203
    Prev
    Next
    INDEX
    Explanations

    code structure and control flow elements within programming context

    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
     Russ
    -0.06
    ANCES
    -0.06
    ombok
    -0.06
    allis
    -0.06
    ALES
    -0.06
    ropp
    -0.06
    ÏĦÏģι
    -0.05
    ookies
    -0.05
    leurs
    -0.05
    urst
    -0.05
    POSITIVE LOGITS
    iminal
    0.07
    eman
    0.07
    egan
    0.07
    $MESS
    0.07
    ureau
    0.07
    owaÄĩ
    0.07
    cano
    0.06
    ÑĤÑĢа
    0.06
    irable
    0.06
    PHA
    0.06
    Activations Density 0.000%

    No Known Activations