© 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. 12-LLAMASCOPE-RES-32K
    11. 13156
    Prev
    Next
    INDEX
    Explanations

    expressions related to predictions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    κο
    -0.18
    uentes
    -0.17
    ระà¸Ķ
    -0.15
     onBind
    -0.15
    ÑĩаÑģÑĤ
    -0.15
    adele
    -0.15
    iti
    -0.14
    ycop
    -0.14
    -Clause
    -0.14
    fdc
    -0.14
    POSITIVE LOGITS
    mine
    0.19
    amil
    0.15
     tern
    0.15
     Aw
    0.14
    erta
    0.14
    zsche
    0.14
     sou
    0.14
     fav
    0.14
     either
    0.14
    eder
    0.14
    Activations Density 0.237%

    No Known Activations