© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    motley fool podcasts

    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
    Slinky
    -0.09
    laden
    -0.09
    abbo
    -0.08
    TransparentColor
    -0.08
    _SB
    -0.08
    abbr
    -0.08
     Stealth
    -0.08
    PACE
    -0.08
     article
    -0.08
     Fet
    -0.08
    POSITIVE LOGITS
     podcast
    0.22
    pod
    0.20
     pod
    0.19
    Pod
    0.18
     Pod
    0.17
     podcasts
    0.16
     Podcast
    0.16
    odcast
    0.16
    _pod
    0.16
     Revision
    0.13
    Activations Density 0.050%

    No Known Activations