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. 74932
    Prev
    Next
    INDEX
    Explanations

    mentions of permanence and enduring effects in various 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
    AGED
    -0.07
    £½
    -0.06
    ikel
    -0.06
    aur
    -0.06
     Pai
    -0.06
     mish
    -0.06
    180
    -0.06
    पर
    -0.06
     latter
    -0.06
    ako
    -0.06
    POSITIVE LOGITS
    ablish
    0.08
    -lasting
    0.08
    tach
    0.08
    ly
    0.08
    dere
    0.07
     effects
    0.07
    redient
    0.07
     impression
    0.07
    -LAST
    0.07
    .fm
    0.07
    Activations Density 0.008%

    No Known Activations