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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 16960
    Prev
    Next
    INDEX
    Explanations

    references to censorship and controversial speech issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     localVar
    -0.14
    lint
    -0.14
    olumn
    -0.14
    æķĻ
    -0.14
     Santana
    -0.13
    GS
    -0.13
    usat
    -0.13
     Morav
    -0.13
    opup
    -0.13
    383
    -0.13
    POSITIVE LOGITS
     Alt
    0.38
     alt
    0.37
    Alt
    0.35
    -alt
    0.32
     ALT
    0.29
    .alt
    0.27
    _alt
    0.27
    ALT
    0.26
     Milo
    0.25
    alt
    0.24
    Activations Density 0.081%

    No Known Activations