© 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. 83169
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common punctuation marks and short evaluative phrases that facilitate text flow and transitions between ideas.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Oh
    -0.06
    eyn
    -0.06
    eton
    -0.06
    UNE
    -0.06
    åĩ½
    -0.06
     Abraham
    -0.06
    une
    -0.06
    antt
    -0.06
    ëŀ
    -0.06
     Lif
    -0.06
    POSITIVE LOGITS
     fine
    0.25
     Fine
    0.22
    fine
    0.22
    Fine
    0.20
    FINE
    0.15
     ok
    0.14
     okay
    0.13
     OK
    0.13
    _FINE
    0.12
    OK
    0.12
    Activations Density 0.102%

    No Known Activations