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. 12-LLAMASCOPE-RES-32K
    6. 14020
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments, inconsistencies, and challenges in reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jerne
    -0.17
     :č↵
    -0.15
    igner
    -0.14
    ows
    -0.14
    .AppendFormat
    -0.14
    assa
    -0.14
    ammen
    -0.14
    ucher
    -0.13
    lename
    -0.13
    holder
    -0.13
    POSITIVE LOGITS
    ;;;;
    0.15
    Inlining
    0.15
    alon
    0.15
    æ£
    0.15
     Ging
    0.15
    viÄį
    0.14
    adol
    0.14
    orraine
    0.14
    isy
    0.14
     bol
    0.13
    Activations Density 0.232%

    No Known Activations