© 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. 93476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or ways to accomplish tasks

    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
    deo
    -0.08
    ãĥ«ãĤ¯
    -0.07
    conditional
    -0.07
    UNUSED
    -0.07
    ãĥīãĥ«
    -0.07
     ÐijоÑĢ
    -0.07
    ãģ®æĸ¹
    -0.07
    kır
    -0.07
    REATED
    -0.07
    entai
    -0.07
    POSITIVE LOGITS
     except
    0.12
    except
    0.10
     unless
    0.10
    unless
    0.08
     Except
    0.08
    Except
    0.08
    aside
    0.08
    urre
    0.08
     nor
    0.07
     easy
    0.07
    Activations Density 0.022%

    No Known Activations