© 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. 28456
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "locking" or "locked."

    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
    ois
    -0.19
    ccione
    -0.18
     Birch
    -0.16
    phere
    -0.15
    è´¹
    -0.15
    pill
    -0.15
    важа
    -0.15
    湯
    -0.15
     Roller
    -0.14
    (pol
    -0.14
    POSITIVE LOGITS
    tober
    0.27
    (lock
    0.23
    heed
    0.23
    ombo
    0.22
    hart
    0.22
    .Lock
    0.22
     Locked
    0.21
    .mutex
    0.20
    locked
    0.20
     LOCK
    0.19
    Activations Density 0.023%

    No Known Activations