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. 19389
    Prev
    Next
    INDEX
    Explanations

    the prefix "hyper" associated with various medical and psychological conditions

    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
    sb
    -0.20
    sburg
    -0.20
    sk
    -0.20
    serv
    -0.19
    sWith
    -0.19
    sr
    -0.18
    ainless
    -0.18
    side
    -0.18
    sa
    -0.18
    evi
    -0.18
    POSITIVE LOGITS
    bole
    0.35
    icum
    0.25
    active
    0.24
    links
    0.23
    activity
    0.23
    bol
    0.23
    thy
    0.23
    nym
    0.22
    acus
    0.21
    ther
    0.20
    Activations Density 0.005%

    No Known Activations