Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 22496
    Prev
    Next
    INDEX
    Explanations

    negative descriptors related to emotional distress or trauma

    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
    estone
    -0.17
    ep
    -0.16
    taire
    -0.15
    ÑĤал
    -0.15
    eps
    -0.15
    gen
    -0.14
    ãĥ¼ãĤ¿ãĥ¼
    -0.14
    YE
    -0.14
    ichael
    -0.13
    nu
    -0.13
    POSITIVE LOGITS
    rowing
    0.36
    angu
    0.27
    row
    0.27
    ried
    0.26
    rying
    0.24
    ROW
    0.20
     row
    0.20
    rows
    0.19
    ry
    0.19
    icut
    0.19
    Activations Density 0.005%

    No Known Activations