© 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. 94214
    Prev
    Next
    INDEX
    Explanations

    complex and impactful concepts related to fear and challenges in life

    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
    -lfs
    -0.07
     repercussions
    -0.06
    ][(
    -0.06
     promin
    -0.06
     Couple
    -0.06
    things
    -0.06
     justice
    -0.06
     reperc
    -0.06
     couple
    -0.06
    ertools
    -0.06
    POSITIVE LOGITS
     own
    0.14
    own
    0.11
    _own
    0.08
    orman
    0.08
    Own
    0.08
    OWN
    0.08
     Own
    0.07
     allotted
    0.07
    878
    0.07
     chosen
    0.07
    Activations Density 0.133%

    No Known Activations