© 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. 6-LLAMASCOPE-RES-32K
    11. 28004
    Prev
    Next
    INDEX
    Explanations

    Java method invocations and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itler
    -0.18
    ebek
    -0.15
    ierz
    -0.15
    Äįer
    -0.15
    ocol
    -0.14
    æĺŃ
    -0.14
    oslav
    -0.14
    Uvs
    -0.14
    unker
    -0.14
    assic
    -0.14
    POSITIVE LOGITS
     GLES
    0.14
    tn
    0.14
    íĮ¨
    0.13
    :request
    0.13
    tm
    0.13
     RectTransform
    0.13
    .sourceforge
    0.13
    t
    0.13
     Shea
    0.12
    ãģ¬
    0.12
    Activations Density 0.259%

    No Known Activations