© 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. 17-LLAMASCOPE-RES-131K
    6. 71156
    Prev
    Next
    INDEX
    Explanations

    phrases related to citation and referencing

    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
    åģ¥
    -0.08
    acht
    -0.06
     Americas
    -0.06
    .yy
    -0.06
    .avi
    -0.06
     realised
    -0.06
    ixo
    -0.06
     lob
    -0.06
     ‘
    -0.06
    ocks
    -0.05
    POSITIVE LOGITS
    éru
    0.07
    stateProvider
    0.07
     oneself
    0.07
     konkrét
    0.07
    agens
    0.07
    rové
    0.07
    shima
    0.06
    assin
    0.06
    rist
    0.06
     доÑģÑĤ
    0.06
    Activations Density 0.003%

    No Known Activations