© 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. 28880
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    lse
    -0.07
    cdn
    -0.07
    ville
    -0.07
    ALI
    -0.07
    erais
    -0.07
    /documentation
    -0.07
    Äįer
    -0.07
    EDIA
    -0.07
    reira
    -0.07
    ike
    -0.07
    POSITIVE LOGITS
     it
    0.10
     there
    0.10
     this
    0.07
    there
    0.07
     everything
    0.06
    obe
    0.06
    akes
    0.06
    /stdc
    0.06
    olate
    0.06
    iffin
    0.06
    Activations Density 0.007%

    No Known Activations