© 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. 126378
    Prev
    Next
    INDEX
    Explanations

    concepts related to analysis and comparison of data sets

    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
    enco
    -0.07
     free
    -0.06
     new
    -0.06
    ande
    -0.06
     etc
    -0.06
    ioni
    -0.06
    iry
    -0.06
    ovel
    -0.06
    iona
    -0.06
     Snow
    -0.05
    POSITIVE LOGITS
    overall
    0.08
    ãĥ¼ãĤ¹ãĥĪ
    0.08
     overall
    0.07
    Overall
    0.07
     Overall
    0.07
     záp
    0.07
    except
    0.06
     Tradable
    0.06
     =================================================================================
    0.06
     Reform
    0.06
    Activations Density 0.003%

    No Known Activations