© 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. 78163
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'b' in various contexts

    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
    ern
    -0.08
    igans
    -0.08
    å·»
    -0.08
    mlin
    -0.07
    adin
    -0.07
    igar
    -0.07
    andas
    -0.07
    overs
    -0.07
    UILayout
    -0.07
    ETY
    -0.07
    POSITIVE LOGITS
    ende
    0.06
    older
    0.05
    ex
    0.05
    immer
    0.05
     Lester
    0.05
     ro
    0.05
    sb
    0.05
    accel
    0.05
    Net
    0.05
     Ad
    0.05
    Activations Density 0.040%

    No Known Activations