© 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. 29-LLAMASCOPE-RES-32K
    11. 19245
    Prev
    Next
    INDEX
    Explanations

    keywords related to professional roles and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢĤèĢĮ
    -0.16
     Wich
    -0.15
    eling
    -0.15
    ifr
    -0.15
    IFS
    -0.14
    CHK
    -0.14
    IF
    -0.14
    >;
    -0.14
    olders
    -0.14
    нÑıÑĤ
    -0.14
    POSITIVE LOGITS
    —is
    0.44
    —are
    0.38
    -has
    0.34
    ï¼īãģ¯
    0.33
    -is
    0.29
    )ëĬĶ
    0.28
    "is
    0.27
    )did
    0.27
    )ìĿĢ
    0.27
    -can
    0.26
    Activations Density 0.039%

    No Known Activations