© 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. 17010
    Prev
    Next
    INDEX
    Explanations

    references to programming and configuration processes

    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
    ebek
    -0.15
    бо
    -0.14
    asıyla
    -0.13
    θμ
    -0.12
    !(
    -0.12
    [:]
    -0.12
    èĩªæ²»
    -0.12
    atism
    -0.12
    âĢ¦but
    -0.11
    Ùĭ
    -0.11
    POSITIVE LOGITS
     ustanov
    0.18
    liest
    0.17
    微软éĽħé»ij
    0.15
    å®ĭä½ĵ
    0.15
    STITUTE
    0.14
     ActionTypes
    0.14
    stitute
    0.14
    ovna
    0.14
    RefPtr
    0.13
    /current
    0.13
    Activations Density 1.303%

    No Known Activations