© 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. 15-LLAMASCOPE-RES-131K
    11. 103843
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions, specifications, or criteria 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
    alles
    -0.08
    .btnAdd
    -0.07
    roker
    -0.07
    æ³ģ
    -0.07
    olley
    -0.07
    å®ı
    -0.06
    اØŃÛĮ
    -0.06
    HWND
    -0.06
    idUser
    -0.06
    apel
    -0.06
    POSITIVE LOGITS
     certain
    0.14
     Certain
    0.11
    Certain
    0.10
     bestimm
    0.08
     certains
    0.08
     specific
    0.07
     specified
    0.07
     kinds
    0.07
     types
    0.07
    ertain
    0.07
    Activations Density 0.036%

    No Known Activations