© 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. 15-LLAMASCOPE-RES-32K
    6. 8218
    Prev
    Next
    INDEX
    Explanations

    terms related to the need for further inquiry or deserving attention and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acad
    -0.16
    udad
    -0.15
    erus
    -0.15
    eniz
    -0.15
     ý
    -0.15
    wap
    -0.15
    meli
    -0.14
    θμ
    -0.14
    piration
    -0.14
    Barrier
    -0.14
    POSITIVE LOGITS
     attention
    0.19
     grabs
    0.18
     scrutiny
    0.17
     review
    0.16
     вним
    0.16
     comparison
    0.15
    283
    0.15
     investigation
    0.15
     consideration
    0.15
    ëĭ¹
    0.15
    Activations Density 0.184%

    No Known Activations