© 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. 3741
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    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
    .LOGIN
    -0.08
    __$
    -0.08
    ÙĮ
    -0.08
    ýt
    -0.08
    лиÑħ
    -0.08
     KromÄĽ
    -0.08
    .Formatter
    -0.07
    AGMA
    -0.07
     NÄĽk
    -0.07
    ̣
    -0.07
    POSITIVE LOGITS
    /if
    0.07
     underway
    0.06
    nt
    0.06
    onna
    0.06
     OTHERWISE
    0.06
     otherwise
    0.06
    PP
    0.06
     slightest
    0.06
     finished
    0.06
    orie
    0.06
    Activations Density 0.039%

    No Known Activations