© 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. 22-LLAMASCOPE-RES-131K
    11. 4126
    Prev
    Next
    INDEX
    Explanations

    references to legal issues and violations

    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
    _rnn
    -0.06
     primes
    -0.06
     char
    -0.06
     Coc
    -0.05
    оÑģÑĮ
    -0.05
     eth
    -0.05
     vault
    -0.05
     Morse
    -0.05
     dood
    -0.05
    art
    -0.05
    POSITIVE LOGITS
     ticket
    0.22
     tickets
    0.20
     citation
    0.18
     Tickets
    0.18
     Ticket
    0.17
    -ticket
    0.17
     citations
    0.17
    ticket
    0.17
    tickets
    0.16
    Tickets
    0.15
    Activations Density 0.063%

    No Known Activations