© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76673
    Prev
    Next
    INDEX
    Explanations

    frequency of personal pronouns in the text

    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
    odore
    -0.06
    abella
    -0.06
    af
    -0.06
    ÅĤe
    -0.06
    ovan
    -0.06
    :
    -0.06
     Charge
    -0.06
    amen
    -0.06
     �
    -0.05
    rence
    -0.05
    POSITIVE LOGITS
    eded
    0.08
    tas
    0.08
    athed
    0.07
    麼
    0.07
    iling
    0.07
    #ac
    0.07
     gros
    0.07
     Crosby
    0.07
    OOK
    0.07
    ilers
    0.07
    Activations Density 0.099%

    No Known Activations