© 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. 3713
    Prev
    Next
    INDEX
    Explanations

    phrases related to justification and the necessity of explanations or reasons

    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
    ernes
    -0.08
    á»ĵ
    -0.07
    /effects
    -0.07
    urr
    -0.07
    ffects
    -0.07
    .actions
    -0.07
    Verb
    -0.07
    eko
    -0.07
    Leaf
    -0.07
     اعتÙħاد
    -0.07
    POSITIVE LOGITS
     justify
    0.14
     justification
    0.13
     reasons
    0.12
     Reasons
    0.11
     justified
    0.11
     rationale
    0.10
     reason
    0.10
    justify
    0.10
    reason
    0.10
    Reason
    0.10
    Activations Density 0.022%

    No Known Activations