© 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. 33894
    Prev
    Next
    INDEX
    Explanations

    validity

    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
    ValidationError
    -0.10
    anan
    -0.10
    Validation
    -0.10
    _validation
    -0.10
    <|begin_of_text|>
    -0.09
    -validation
    -0.09
    erg
    -0.09
    olulu
    -0.09
    orra
    -0.09
    LEMENT
    -0.09
    POSITIVE LOGITS
    ating
    0.28
    ly
    0.27
    ated
    0.26
    atable
    0.26
    ity
    0.21
    ations
    0.20
    /legal
    0.19
    ates
    0.18
    ATED
    0.17
    s
    0.15
    Activations Density 0.022%

    No Known Activations