© 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. 29492
    Prev
    Next
    INDEX
    Explanations

    the word "of" 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
    ying
    -0.07
    sy
    -0.06
    iy
    -0.06
    ensa
    -0.06
    yles
    -0.06
    å¤Ħ
    -0.06
    ket
    -0.06
    KEN
    -0.06
    KN
    -0.06
    Serialization
    -0.05
    POSITIVE LOGITS
    udad
    0.07
    ILON
    0.06
    ίÏĥ
    0.06
    話
    0.06
    á»ĵi
    0.06
    ĥģ
    0.06
    /**č↵
    0.06
    ecut
    0.06
    ãĤĬãģ¨
    0.06
    unos
    0.06
    Activations Density 0.053%

    No Known Activations