© 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. 18-LLAMASCOPE-RES-32K
    11. 2987
    Prev
    Next
    INDEX
    Explanations

    words that indicate companionship or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pty
    -0.16
    ppe
    -0.16
    OMATIC
    -0.14
    IFORM
    -0.14
    ookie
    -0.14
    ESH
    -0.14
    _MAY
    -0.14
    jection
    -0.14
    sse
    -0.14
    ookies
    -0.14
    POSITIVE LOGITS
     foes
    0.22
     enemies
    0.21
     foe
    0.21
     enemy
    0.20
     Enemies
    0.17
    Enemies
    0.17
     acquaint
    0.17
     relatives
    0.17
    enemy
    0.16
     family
    0.15
    Activations Density 0.034%

    No Known Activations