© 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. 106448
    Prev
    Next
    INDEX
    Explanations

    characters or punctuation marks typically found in technical and programming contexts

    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
    alah
    -0.06
    ибли
    -0.06
    -imm
    -0.06
    yz
    -0.06
    assed
    -0.06
     Pul
    -0.06
    uzzle
    -0.06
    acco
    -0.06
    iones
    -0.06
    dac
    -0.06
    POSITIVE LOGITS
    lander
    0.08
    Ĺi
    0.07
    «ĺ
    0.07
     Buccane
    0.07
    #__
    0.07
    iveau
    0.07
    linger
    0.07
    بÙĪد
    0.07
    239
    0.07
    Ĺ
    0.06
    Activations Density 0.000%

    No Known Activations