© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 19172
    Prev
    Next
    INDEX
    Explanations

    information related to legislative bans and regulations

    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
    owitz
    -0.18
    unga
    -0.14
    olla
    -0.14
    Ñİдж
    -0.14
    loff
    -0.14
    елиÑĩ
    -0.14
    Įĵ
    -0.14
     Affero
    -0.13
    olas
    -0.13
    ypass
    -0.13
    POSITIVE LOGITS
     ban
    0.69
     bans
    0.57
     Ban
    0.57
    ban
    0.54
     banned
    0.52
    Ban
    0.52
     banning
    0.51
    ç¦ģæŃ¢
    0.43
     Bans
    0.41
     prohibition
    0.40
    Activations Density 0.267%

    No Known Activations