© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 4352
    Prev
    Next
    INDEX
    Explanations

    effectiveness or outcomes

    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
    NewProp
    -0.10
    (éĩij
    -0.09
    _traits
    -0.09
    Unavailable
    -0.09
     unrecognized
    -0.08
    shima
    -0.08
    jadi
    -0.08
    mür
    -0.08
    ttp
    -0.08
     lateral
    -0.08
    POSITIVE LOGITS
     effectiveness
    0.38
     implementation
    0.24
     efficacy
    0.24
     success
    0.24
    æķĪæŀľ
    0.21
     Implementation
    0.21
    ffic
    0.20
    implementation
    0.20
    Implementation
    0.19
     effective
    0.19
    Activations Density 0.099%

    No Known Activations