© 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. 84056
    Prev
    Next
    INDEX
    Explanations

    references to deletion or removing items 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
    lo
    -0.07
    ÃĻ
    -0.07
    YLES
    -0.07
    sez
    -0.07
    lero
    -0.07
    InChildren
    -0.07
    ilities
    -0.07
    lov
    -0.07
    nut
    -0.07
    YNC
    -0.07
    POSITIVE LOGITS
    /add
    0.08
    oxy
    0.07
    æİī
    0.07
    erp
    0.07
    iert
    0.07
    acro
    0.07
    itto
    0.07
    /disable
    0.07
    CriticalSection
    0.06
    imer
    0.06
    Activations Density 0.007%

    No Known Activations