© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44285
    Prev
    Next
    INDEX
    Explanations

    to install or mount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rudd
    -0.10
     Stra
    -0.09
     Vere
    -0.09
     underground
    -0.08
    .Networking
    -0.08
    NL
    -0.08
     Lob
    -0.08
     Bom
    -0.08
    land
    -0.08
     drum
    -0.08
    POSITIVE LOGITS
     mount
    0.39
     Mount
    0.34
    Mount
    0.32
    mount
    0.32
    .mount
    0.28
     mounts
    0.27
    -mount
    0.26
     mounting
    0.25
    _mount
    0.21
     mounted
    0.20
    Activations Density 0.044%

    No Known Activations