© 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. 29-LLAMASCOPE-RES-32K
    11. 18200
    Prev
    Next
    INDEX
    Explanations

    words and prefixes related to renewal or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iel
    -0.16
    .sourceforge
    -0.15
    osh
    -0.15
    AndWait
    -0.14
     vom
    -0.14
    struction
    -0.14
     zi
    -0.14
    yb
    -0.14
    lug
    -0.14
    ãĤ²
    -0.13
    POSITIVE LOGITS
    kind
    0.34
     kind
    0.25
    establish
    0.24
    Kind
    0.23
    assert
    0.22
     KIND
    0.22
    uint
    0.22
    -kind
    0.21
    .kind
    0.20
    ener
    0.20
    Activations Density 0.026%

    No Known Activations