© 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. 28-LLAMASCOPE-RES-32K
    11. 21190
    Prev
    Next
    INDEX
    Explanations

    references to numeric identifiers and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adays
    -0.33
    etheless
    -0.32
    odore
    -0.32
    OGLE
    -0.30
    atre
    -0.23
    AGEMENT
    -0.23
    ERRUPT
    -0.23
    esda
    -0.23
    SACTION
    -0.22
    ÑįÑĤомÑĥ
    -0.22
    POSITIVE LOGITS
    ROID
    0.19
    ContentLoaded
    0.17
    sip
    0.15
    erro
    0.15
    tin
    0.15
    pires
    0.14
    aunch
    0.14
    ipple
    0.14
    ses
    0.14
    atoes
    0.14
    Activations Density 0.182%

    No Known Activations