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. 9-LLAMASCOPE-RES-131K
    6. 95759
    Prev
    Next
    INDEX
    Explanations

    structure and references related to job listings and appointments

    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
    INGER
    -0.08
    ä¸Ķ
    -0.07
     Hlav
    -0.07
    inger
    -0.07
    ellas
    -0.06
    PÅĻÃŃ
    -0.06
    .backends
    -0.06
    otos
    -0.06
    .compress
    -0.06
    Sha
    -0.06
    POSITIVE LOGITS
    lingen
    0.08
    uts
    0.07
     Chore
    0.06
    433
    0.06
    oren
    0.06
    oba
    0.06
    ests
    0.06
    ij
    0.06
    ade
    0.06
    ources
    0.06
    Activations Density 0.050%

    No Known Activations