© 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. 18313
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    話
    -0.15
     sla
    -0.15
     ÙħتÙĨ
    -0.14
    otos
    -0.14
    stown
    -0.14
    ead
    -0.14
     County
    -0.14
    fet
    -0.14
    olders
    -0.14
    ondo
    -0.13
    POSITIVE LOGITS
    odia
    0.26
    wal
    0.25
    oria
    0.21
    olia
    0.21
    adoo
    0.20
    vala
    0.18
    horia
    0.18
    deo
    0.18
     Roy
    0.18
    kar
    0.18
    Activations Density 0.098%

    No Known Activations