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. 13-LLAMASCOPE-RES-32K
    6. 15762
    Prev
    Next
    INDEX
    Explanations

    phrases related to directional orientations, particularly "left" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rna
    -0.17
    xl
    -0.16
    รà¸Ńà¸ĩ
    -0.16
    ously
    -0.15
    ouflage
    -0.15
    rå
    -0.15
     Ñįлек
    -0.15
    adil
    -0.15
    ร
    -0.15
    ãģĨãģ¡
    -0.15
    POSITIVE LOGITS
    ward
    0.24
    /right
    0.22
    wards
    0.21
    most
    0.21
    -hand
    0.21
    ness
    0.20
    ablish
    0.18
    tings
    0.18
    -wing
    0.17
    s
    0.16
    Activations Density 0.052%

    No Known Activations