© 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. 25-LLAMASCOPE-RES-32K
    11. 10993
    Prev
    Next
    INDEX
    Explanations

    elements related to social dynamics and problematic behavior

    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
     either
    -0.59
     Either
    -0.54
    either
    -0.52
    Either
    -0.50
     EITHER
    -0.48
     либо
    -0.28
     soit
    -0.25
    ither
    -0.20
     OTHERWISE
    -0.18
    ichever
    -0.18
    POSITIVE LOGITS
     nor
    0.94
    nor
    0.66
     Nor
    0.63
     NOR
    0.58
    Nor
    0.57
     nors
    0.35
     ноÑĢ
    0.29
     neither
    0.29
     né
    0.29
     Norris
    0.28
    Activations Density 0.021%

    No Known Activations