© 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. 25-LLAMASCOPE-RES-32K
    11. 19098
    Prev
    Next
    INDEX
    Explanations

    references to emotional bonds and expressions of affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -0.49
    nya
    -0.46
    ìĿĦ
    -0.42
    so
    -0.41
    sWith
    -0.40
    ne
    -0.39
    ship
    -0.35
    sh
    -0.34
    name
    -0.33
    land
    -0.32
    POSITIVE LOGITS
    urope
    0.27
    e
    0.26
    aux
    0.26
    ÙĶ
    0.26
    eeee
    0.25
    urs
    0.25
    able
    0.25
    y
    0.25
    iro
    0.24
    Ìģ
    0.23
    Activations Density 1.397%

    No Known Activations