© 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. 11-LLAMASCOPE-RES-32K
    11. 1264
    Prev
    Next
    INDEX
    Explanations

    instances of observing or discovering events or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osit
    -0.18
    ãĥ³ãĥĨ
    -0.15
    igo
    -0.15
    ullan
    -0.14
    anti
    -0.14
    icho
    -0.14
    intros
    -0.14
    atcher
    -0.14
    undler
    -0.14
    arm
    -0.13
    POSITIVE LOGITS
    dash
    0.17
    irut
    0.15
     hur
    0.15
    gross
    0.14
    raquo
    0.14
    <::
    0.14
    vie
    0.14
    ÑĢÑĥÑĩ
    0.13
    SetActive
    0.13
    .throw
    0.13
    Activations Density 0.118%

    No Known Activations