© 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. 30-LLAMASCOPE-RES-32K
    11. 23292
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the character 'X' in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    X
    -0.28
    M
    -0.27
    T
    -0.25
    XXXX
    -0.25
    XX
    -0.23
    XXX
    -0.23
    XL
    -0.23
    XXXXXXXX
    -0.23
    XD
    -0.22
    C
    -0.22
    POSITIVE LOGITS
    e
    0.22
    oÃłi
    0.20
    BX
    0.20
    o
    0.17
    NUM
    0.17
    yz
    0.17
    DG
    0.17
    RD
    0.16
    y
    0.16
    MAS
    0.16
    Activations Density 0.031%

    No Known Activations