© 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. 9-LLAMASCOPE-RES-32K
    11. 4259
    Prev
    Next
    INDEX
    Explanations

    mentions of funding for projects or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weed
    -0.13
    odata
    -0.13
     weed
    -0.13
     quiet
    -0.13
    .pb
    -0.13
     refr
    -0.12
    alted
    -0.12
    anou
    -0.12
    umer
    -0.12
     inner
    -0.12
    POSITIVE LOGITS
     sez
    0.16
    .INSTANCE
    0.15
    igram
    0.15
    cente
    0.14
    ipl
    0.13
    íĥĦ
    0.13
    cec
    0.13
    onta
    0.13
     Dün
    0.13
    ITS
    0.13
    Activations Density 6.083%

    No Known Activations