© 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. 28961
    Prev
    Next
    INDEX
    Explanations

    references to advertisements and promotional content

    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
     instead
    -0.09
     вмеÑģÑĤ
    -0.08
    instead
    -0.07
     b
    -0.06
     "
    -0.06
     (
    -0.06
    -0.06
     except
    -0.06
     Vu
    -0.06
     '
    -0.06
    POSITIVE LOGITS
     alone
    0.14
    alone
    0.12
     Alone
    0.12
    .scalablytyped
    0.10
     seule
    0.10
    -alone
    0.10
    Statics
    0.09
    Solo
    0.09
     anymore
    0.09
     seul
    0.08
    Activations Density 0.026%

    No Known Activations