© 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. 15-LLAMASCOPE-RES-131K
    6. 104009
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its various contextually related forms

    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
    igin
    -0.07
    InputLabel
    -0.07
    roperty
    -0.07
    MethodImpl
    -0.07
    etails
    -0.07
    ationToken
    -0.06
    EDIA
    -0.06
    adan
    -0.06
    ]=>
    -0.06
    βολ
    -0.06
    POSITIVE LOGITS
    uddle
    0.07
     either
    0.07
    engo
    0.07
    itore
    0.06
     Glas
    0.06
    ?a
    0.06
    rops
    0.06
     Net
    0.06
    408
    0.06
     Netz
    0.06
    Activations Density 0.006%

    No Known Activations