Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 27960
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to populations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _blob
    -0.13
    ůst
    -0.13
    θι
    -0.13
    stvÃŃ
    -0.13
     опеÑĢа
    -0.13
    ç·Ĭ
    -0.13
    ouz
    -0.13
    733
    -0.13
    ')==
    -0.12
    à¥įशन
    -0.12
    POSITIVE LOGITS
     population
    1.10
     Population
    0.94
    population
    0.92
    Population
    0.86
     pop
    0.84
     populations
    0.84
     Pop
    0.77
    _population
    0.77
    pop
    0.75
    -pop
    0.75
    Activations Density 0.222%

    No Known Activations