© 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 (Instruct)
    5. 50-RESID-POST-GF
    7. 34150
    Prev
    Next
    INDEX
    Explanations

    future actions or states

    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
     coincide
    -0.09
     Äijã
    -0.08
    oret
    -0.08
    eli
    -0.08
    487
    -0.08
    els
    -0.08
     Bew
    -0.08
    ubb
    -0.08
    оÑĢоÑĤ
    -0.08
    alla
    -0.08
    POSITIVE LOGITS
     be
    0.20
    iams
    0.18
     likely
    0.17
    iam
    0.16
     pocházet
    0.14
     need
    0.14
    l
    0.14
     require
    0.13
    fully
    0.13
    likely
    0.12
    Activations Density 0.067%

    No Known Activations