© 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. 24-LLAMASCOPE-RES-32K
    11. 15118
    Prev
    Next
    INDEX
    Explanations

    the word "with" and its usage in various contexts, particularly in programming or descriptions of data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uby
    -0.15
    utdown
    -0.15
     calle
    -0.15
    undi
    -0.14
    QObject
    -0.14
     patt
    -0.14
    ç¿°
    -0.14
    .methods
    -0.14
    ÑĢÑĥн
    -0.13
    street
    -0.13
    POSITIVE LOGITS
     open
    0.39
    open
    0.29
    (open
    0.26
    -open
    0.21
    .open
    0.20
    =open
    0.19
     açık
    0.18
     оÑĤкÑĢÑĭÑĤ
    0.18
    .assertRaises
    0.18
    	open
    0.18
    Activations Density 0.007%

    No Known Activations