© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56325
    Prev
    Next
    INDEX
    Explanations

    terms related to self-sufficiency and sustainable living practices

    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
    linger
    -0.07
    caffe
    -0.07
    elite
    -0.07
    Ñĥй
    -0.07
    avana
    -0.07
    маз
    -0.07
    åĭ
    -0.06
     briefing
    -0.06
     chocolates
    -0.06
    elib
    -0.06
    POSITIVE LOGITS
     self
    0.09
     survival
    0.08
     subs
    0.08
    911
    0.07
     Self
    0.07
    ç«ĭãģ¦
    0.07
     Survival
    0.07
     store
    0.07
     home
    0.07
     household
    0.07
    Activations Density 0.061%

    No Known Activations