© 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. 71419
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online content

    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
    zac
    -0.06
    orney
    -0.06
    amo
    -0.05
     lineWidth
    -0.05
     Rafael
    -0.05
    quip
    -0.05
    ork
    -0.05
    aran
    -0.05
     Pap
    -0.05
     head
    -0.05
    POSITIVE LOGITS
    ivery
    0.08
     Licht
    0.07
     migrationBuilder
    0.07
    Ø´ÙĪ
    0.07
    (PR
    0.07
    eon
    0.07
    GenerationStrategy
    0.07
    ://
    0.06
    æ·»
    0.06
    lore
    0.06
    Activations Density 0.000%

    No Known Activations