© 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. 76798
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of translation or converting one thing into another

    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
    iw
    -0.07
    _PARTITION
    -0.07
    nest
    -0.07
    Ìĥ
    -0.07
    hiro
    -0.07
    ok
    -0.06
    รม
    -0.06
    think
    -0.06
    AGMA
    -0.06
    ukan
    -0.06
    POSITIVE LOGITS
     into
    0.12
     onto
    0.09
     Into
    0.09
    Into
    0.09
    into
    0.08
    _into
    0.07
    onto
    0.07
     translates
    0.07
     translated
    0.07
     translate
    0.07
    Activations Density 0.007%

    No Known Activations