© 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 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. 25-LLAMASCOPE-RES-32K
    11. 12411
    Prev
    Next
    INDEX
    Explanations

    motifs related to censorship and freedom of expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stim
    -0.17
     discharged
    -0.15
     Collapse
    -0.14
    ÑĢÑĮ
    -0.14
    ìĦĿ
    -0.14
    CRM
    -0.14
    778
    -0.14
     abandonment
    -0.13
    ÑĤÑĢон
    -0.13
    abyrin
    -0.13
    POSITIVE LOGITS
     censor
    0.51
     censorship
    0.51
     c
    0.45
    ensored
    0.32
    ensor
    0.32
     ÑĨ
    0.29
    Âłc
    0.27
     blocked
    0.25
    c
    0.25
     filtering
    0.25
    Activations Density 0.153%

    No Known Activations