© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84570
    Prev
    Next
    INDEX
    Explanations

    references to the concept of utility and its applications

    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
    esel
    -0.07
    ÑģÑĤÑİ
    -0.07
    lied
    -0.07
    edb
    -0.07
    ìĪł
    -0.07
    Parking
    -0.07
    eyed
    -0.07
    /unit
    -0.07
    liness
    -0.07
    esis
    -0.06
    POSITIVE LOGITS
    itarian
    0.10
    isateur
    0.10
    izing
    0.07
    imately
    0.07
    ization
    0.07
    rea
    0.07
    mania
    0.07
    opian
    0.07
    longleftrightarrow
    0.07
    ising
    0.07
    Activations Density 0.005%

    No Known Activations