© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 4832
    Prev
    Next
    INDEX
    Explanations

    negations and words that imply uncertainty or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chest
    -0.18
    atcher
    -0.15
    ãĤ¹ãĥĨãĤ£
    -0.15
    fx
    -0.15
    oz
    -0.15
     Ú¯ÛĮ
    -0.15
    empor
    -0.14
     now
    -0.14
    acia
    -0.14
    irie
    -0.14
    POSITIVE LOGITS
    оÑĢÑĥж
    0.16
    ypad
    0.15
    _INCLUDE
    0.15
    >\<^
    0.14
    Yesterday
    0.14
    окон
    0.14
    ëĭµ
    0.14
    ản
    0.13
    orte
    0.13
    reon
    0.13
    Activations Density 0.082%

    No Known Activations