© 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. 9-LLAMASCOPE-RES-32K
    11. 4275
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "not yet" or similar expressions indicating something that is pending or unresolved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.17
    de
    -0.14
    ne
    -0.14
    294
    -0.14
    ess
    -0.14
     Woodward
    -0.14
     initial
    -0.13
    راد
    -0.13
    au
    -0.13
    org
    -0.13
    POSITIVE LOGITS
    ablish
    0.17
    ynchronously
    0.15
    onse
    0.15
    Ĥæķ°
    0.15
    'gc
    0.14
    peror
    0.14
    iland
    0.14
     yet
    0.14
    ukkit
    0.14
    Lens
    0.14
    Activations Density 0.036%

    No Known Activations