© 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. 9-LLAMASCOPE-RES-32K
    11. 3636
    Prev
    Next
    INDEX
    Explanations

    references to postal stamps and their descriptions

    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
    431
    -0.17
    248
    -0.16
    247
    -0.16
    239
    -0.15
    amina
    -0.15
     ch
    -0.14
    263
    -0.14
     Curtis
    -0.14
    981
    -0.14
    err
    -0.14
    POSITIVE LOGITS
     Kear
    0.15
    ’e
    0.14
    eres
    0.14
     teb
    0.14
     anthology
    0.14
    erspective
    0.14
    çģ
    0.14
    Syntax
    0.14
    ERING
    0.14
    krit
    0.13
    Activations Density 0.020%

    No Known Activations