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. 13-LLAMASCOPE-RES-32K
    6. 26575
    Prev
    Next
    INDEX
    Explanations

    key phrases and terms related to advice and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ắt
    -0.15
    ,LOCATION
    -0.15
     tiener
    -0.15
    maktan
    -0.15
    orias
    -0.15
    urgent
    -0.15
    adÄĽ
    -0.15
    .yang
    -0.14
    ooth
    -0.14
     Spending
    -0.14
    POSITIVE LOGITS
     æ²
    0.16
    alk
    0.15
    KP
    0.15
    ow
    0.15
    dash
    0.14
    ert
    0.14
     opin
    0.14
    ush
    0.14
    oll
    0.14
    ãĤ¿ãĥ«
    0.14
    Activations Density 0.001%

    No Known Activations