© 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. 28-LLAMASCOPE-RES-32K
    11. 30212
    Prev
    Next
    INDEX
    Explanations

    elements related to anticipatory hints and developments in entertainment media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilde
    -0.15
    ãĥ³ãĥĩãĤ£
    -0.14
    è§
    -0.13
    alez
    -0.13
    inder
    -0.13
     testimon
    -0.13
    Tutorial
    -0.13
    ÙĦاØŃ
    -0.13
     béné
    -0.12
    arrera
    -0.12
    POSITIVE LOGITS
     teas
    0.40
     tease
    0.35
     teased
    0.34
     hint
    0.34
     teasing
    0.33
     crypt
    0.32
     teaser
    0.31
     hints
    0.31
    hint
    0.31
     te
    0.30
    Activations Density 0.156%

    No Known Activations