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. 57360
    Prev
    Next
    INDEX
    Explanations

    references to specific objects, identities, and relations within a narrative 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
    ÅĻad
    -0.09
    iquer
    -0.08
    uzey
    -0.08
    ocop
    -0.08
    ebi
    -0.08
    rowable
    -0.07
    idon
    -0.07
    dsl
    -0.07
    íĦ°
    -0.07
    ucene
    -0.07
    POSITIVE LOGITS
     their
    0.07
     they
    0.06
     its
    0.06
     br
    0.06
     latter
    0.06
     thereof
    0.06
     company
    0.06
     being
    0.05
     Consent
    0.05
     åħį
    0.05
    Activations Density 0.025%

    No Known Activations