© 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. 56399
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ext" and its variations, indicating its focus on extensions and related terms

    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
    irk
    -0.07
    ipeg
    -0.07
    keeping
    -0.07
    peg
    -0.06
    IndexChanged
    -0.06
    estro
    -0.06
    JECT
    -0.06
    ariat
    -0.06
     Pes
    -0.06
    utter
    -0.06
    POSITIVE LOGITS
    inction
    0.10
    remely
    0.10
    /ext
    0.09
    reme
    0.09
    ensive
    0.08
    ention
    0.08
    uber
    0.08
    ̣
    0.08
    rem
    0.08
     ext
    0.08
    Activations Density 0.019%

    No Known Activations