© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 27187
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions used in various contexts

    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
    ihat
    -0.16
     Bowen
    -0.15
    áºŃu
    -0.15
    arkin
    -0.15
     ti
    -0.14
     oblig
    -0.14
    marine
    -0.14
     Marine
    -0.13
    Latch
    -0.13
    uchar
    -0.13
    POSITIVE LOGITS
    åŁº
    0.15
    rze
    0.15
    -automatic
    0.14
     (~(
    0.14
    rary
    0.14
     kenn
    0.14
    matter
    0.14
    urger
    0.14
    &&(
    0.14
    รà¸ģ
    0.14
    Activations Density 0.016%

    No Known Activations