© 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. 27254
    Prev
    Next
    INDEX
    Explanations

    numbers related to statistics or identifiers

    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
    312
    -0.18
    oret
    -0.16
    dorf
    -0.16
     Higgins
    -0.15
    aten
    -0.15
    ardin
    -0.15
    311
    -0.14
    251
    -0.14
    305
    -0.13
    licenses
    -0.13
    POSITIVE LOGITS
    abeth
    0.17
    ÑĢади
    0.17
    982
    0.15
    amodel
    0.14
    iba
    0.14
    ánÃŃm
    0.14
    ISR
    0.14
    antidad
    0.14
    ноÑĪ
    0.14
    jdk
    0.14
    Activations Density 0.001%

    No Known Activations