© 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. 118963
    Prev
    Next
    INDEX
    Explanations

    references to specific characteristics or attributes of subjects in various contexts

    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
     же
    -0.07
    istrovstvÃŃ
    -0.06
     notions
    -0.06
    oise
    -0.06
     notion
    -0.06
    abee
    -0.06
    orge
    -0.06
    orna
    -0.06
    latin
    -0.06
    izar
    -0.06
    POSITIVE LOGITS
    erdem
    0.08
    erosis
    0.07
    ulfilled
    0.07
     MERCHANTABILITY
    0.06
     origin
    0.06
    ocommerce
    0.06
    acyj
    0.06
    ankind
    0.06
     ilk
    0.06
    parator
    0.06
    Activations Density 0.304%

    No Known Activations