© 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. 23-LLAMASCOPE-RES-32K
    11. 30357
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with agreement and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prob
    -0.15
    dney
    -0.12
    ensex
    -0.12
    à¸Ńà¸ļ
    -0.12
    YPRE
    -0.11
    æ³°
    -0.11
    afone
    -0.11
    apol
    -0.10
    CSI
    -0.10
    coration
    -0.10
    POSITIVE LOGITS
     the
    0.47
    	the
    0.32
    the
    0.32
    ,the
    0.29
     The
    0.27
    The
    0.26
    _the
    0.26
    âĢ¦the
    0.24
    .the
    0.24
    	The
    0.22
    Activations Density 7.637%

    No Known Activations