© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90146
    Prev
    Next
    INDEX
    Explanations

    references to data visualization techniques, particularly bar and pie charts

    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
    ÑĥÑĢн
    -0.07
    urger
    -0.07
    ordo
    -0.07
    sez
    -0.07
    arte
    -0.07
    seau
    -0.06
    prak
    -0.06
     Blvd
    -0.06
    ãĤį
    -0.06
    FromClass
    -0.06
    POSITIVE LOGITS
     bars
    0.07
     bar
    0.07
    okit
    0.07
    ÑĢог
    0.06
    obar
    0.06
    phant
    0.06
     Earn
    0.06
    маÑħ
    0.06
    ãĥ¼ãĥ³
    0.06
    ĵĺ
    0.06
    Activations Density 0.017%

    No Known Activations