© 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. 26-LLAMASCOPE-RES-32K
    6. 6420
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of a variety or diversity of options or offerings

    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
    ãĥ³ãĥIJ
    -0.17
    multiple
    -0.17
     âĨĶ
    -0.17
    avo
    -0.16
    onth
    -0.15
    pairs
    -0.15
    大éĩı
    -0.15
    kinson
    -0.14
    ebo
    -0.14
    jerne
    -0.14
    POSITIVE LOGITS
     range
    0.32
     cross
    0.30
     variety
    0.23
     gam
    0.23
    range
    0.21
     array
    0.21
     Cross
    0.20
    vari
    0.20
     ranges
    0.20
     rage
    0.20
    Activations Density 0.045%

    No Known Activations