© 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. 17142
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures and their condition or status

    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
    ixel
    -0.15
    Carthy
    -0.14
     cramped
    -0.14
     opak
    -0.14
    订
    -0.14
     AssemblyTitle
    -0.13
    avax
    -0.13
    ATRIX
    -0.13
     Ledger
    -0.13
    249
    -0.13
    POSITIVE LOGITS
     abandoned
    0.58
     abandonment
    0.53
     abandon
    0.53
     deserted
    0.38
     fors
    0.35
     decay
    0.35
    andoned
    0.35
     abandoning
    0.35
     dil
    0.31
    å¼ĥ
    0.31
    Activations Density 0.203%

    No Known Activations