© 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. 30-LLAMASCOPE-RES-32K
    11. 11037
    Prev
    Next
    INDEX
    Explanations

    identifiers related to specific episodes or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.17
     Semi
    -0.15
    uti
    -0.15
     ExecutionContext
    -0.15
    rlen
    -0.15
    atis
    -0.15
    anca
    -0.15
    oty
    -0.15
    allax
    -0.14
    hift
    -0.14
    POSITIVE LOGITS
    001
    0.47
    002
    0.43
    003
    0.41
    004
    0.36
    005
    0.35
    Û°Û°
    0.33
    006
    0.30
    000
    0.29
    ï¼IJï¼IJ
    0.28
    007
    0.27
    Activations Density 0.016%

    No Known Activations