© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    instances of the word "following" in various contexts or lists

    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
    ottes
    -0.15
    ikel
    -0.15
    aille
    -0.14
     enough
    -0.14
    lio
    -0.14
    иÑģ
    -0.14
    vos
    -0.14
    recated
    -0.14
    bles
    -0.14
     Enough
    -0.14
    POSITIVE LOGITS
    -described
    0.21
     beiden
    0.20
     list
    0.19
    /current
    0.18
     dozen
    0.18
    -list
    0.17
    -not
    0.17
     table
    0.17
     two
    0.16
     steps
    0.16
    Activations Density 0.033%

    No Known Activations