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. 56188
    Prev
    Next
    INDEX
    Explanations

    the concept of trust 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
    tras
    -0.08
    ymous
    -0.08
    tere
    -0.08
    jÅ¡ÃŃ
    -0.08
    .au
    -0.08
    assed
    -0.07
    thon
    -0.07
    theless
    -0.07
    ãĤī
    -0.07
    enas
    -0.07
    POSITIVE LOGITS
    worthy
    0.11
    ee
    0.11
    worth
    0.10
    fully
    0.10
    ful
    0.09
    ably
    0.09
    fulness
    0.09
    ingly
    0.08
    full
    0.08
    ively
    0.07
    Activations Density 0.012%

    No Known Activations