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. 76518
    Prev
    Next
    INDEX
    Explanations

    key qualifications and requirements for job candidates

    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
     Madden
    -0.07
    _GRANTED
    -0.07
    minecraft
    -0.07
     Bradley
    -0.06
    uably
    -0.06
    ania
    -0.06
    .LoggerFactory
    -0.06
     bios
    -0.06
    ByExample
    -0.06
    .Atomic
    -0.06
    POSITIVE LOGITS
     job
    0.07
    orman
    0.06
     JOB
    0.06
     Soft
    0.06
     reject
    0.06
    afx
    0.06
    pf
    0.06
     deal
    0.06
     Job
    0.06
     company
    0.06
    Activations Density 0.031%

    No Known Activations