© 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. 24-LLAMASCOPE-RES-32K
    11. 16337
    Prev
    Next
    INDEX
    Explanations

    questions related to programming and technical inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hlav
    -0.14
     teng
    -0.14
    ebek
    -0.14
     Dol
    -0.13
    INLINE
    -0.13
    ãĥ³ãĥIJ
    -0.13
    GLOSS
    -0.13
    ague
    -0.13
    efs
    -0.13
     ìĹ°ëĿ½
    -0.13
    POSITIVE LOGITS
     Q
    0.21
     Stack
    0.20
     stack
    0.20
     answer
    0.19
     ANSW
    0.19
    answered
    0.19
     Answer
    0.18
     answered
    0.18
     CLOSED
    0.18
     Closed
    0.18
    Activations Density 0.102%

    No Known Activations