Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76535
    Prev
    Next
    INDEX
    Explanations

    negation phrases in various languages

    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
    mente
    -0.08
    gether
    -0.07
    ly
    -0.07
    otto
    -0.07
    rous
    -0.07
    ler
    -0.07
    اسب
    -0.06
    ges
    -0.06
    -ÑĤо
    -0.06
     NOT
    -0.06
    POSITIVE LOGITS
    ori
    0.11
     necessarily
    0.09
     yet
    0.09
    epad
    0.08
    rega
    0.08
    icias
    0.08
    veau
    0.08
    withstanding
    0.07
     surprisingly
    0.07
    å¿ħ
    0.07
    Activations Density 0.012%

    No Known Activations