© 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. 22447
    Prev
    Next
    INDEX
    Explanations

    terms related to irrigation systems and their components

    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
    erville
    -0.19
    mg
    -0.15
    lk
    -0.15
    onica
    -0.15
    tere
    -0.15
    λί
    -0.15
    isz
    -0.15
    θι
    -0.14
    _SCALE
    -0.14
     ifndef
    -0.14
    POSITIVE LOGITS
    (IR
    0.20
    one
    0.20
    quo
    0.17
    mong
    0.16
    bane
    0.16
     newItem
    0.16
    pective
    0.15
    raž
    0.15
    ationally
    0.15
    337
    0.15
    Activations Density 0.045%

    No Known Activations