© 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. 29-LLAMASCOPE-RES-32K
    11. 5492
    Prev
    Next
    INDEX
    Explanations

    references to products and remedies for health-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nose
    -0.20
    nad
    -0.19
    nat
    -0.18
     nasal
    -0.18
     nursing
    -0.18
    nod
    -0.18
     Nose
    -0.17
     noses
    -0.17
     Nursing
    -0.17
    noun
    -0.17
    POSITIVE LOGITS
     Ne
    1.17
    Ne
    1.07
     ne
    1.00
    -ne
    0.93
    _ne
    0.92
     NE
    0.92
    .ne
    0.87
    ne
    0.85
    (ne
    0.80
    NE
    0.79
    Activations Density 0.193%

    No Known Activations