Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 25548
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and expressions conveying admiration or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rote
    -0.15
    upply
    -0.15
    oa
    -0.15
    ='".$_
    -0.15
    anos
    -0.14
    veau
    -0.14
    éī
    -0.14
     subsidi
    -0.14
     Canter
    -0.14
    izm
    -0.13
    POSITIVE LOGITS
     tslib
    0.17
    timeofday
    0.15
    nock
    0.15
     bunch
    0.15
    jÃŃm
    0.14
    jÃŃ
    0.14
    OOK
    0.14
    ÐIJÑĢÑħÑĸв
    0.14
    -fw
    0.14
    ãĤµãĤ¤
    0.13
    Activations Density 0.076%

    No Known Activations