© 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. 12632
    Prev
    Next
    INDEX
    Explanations

    different strategies or methods regarding various topics

    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
    errals
    -0.17
    rypted
    -0.16
    н
    -0.15
    iggers
    -0.15
    redient
    -0.15
    ansi
    -0.15
    ãĥ¼ãĥĦ
    -0.15
    vez
    -0.15
    enties
    -0.15
    ized
    -0.14
    POSITIVE LOGITS
    able
    0.35
    (es
    0.32
     taken
    0.24
     towards
    0.23
    ability
    0.23
     Taken
    0.22
     toward
    0.22
    ement
    0.21
    esto
    0.20
    sing
    0.20
    Activations Density 0.022%

    No Known Activations