© 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. 4-LLAMASCOPE-RES-32K
    11. 14764
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe triangular shapes or formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boone
    -0.18
    altung
    -0.16
    aque
    -0.15
    opis
    -0.15
    ì¸
    -0.15
    æķ£
    -0.14
    æıı
    -0.14
    aight
    -0.14
    apons
    -0.14
    èĶ
    -0.14
    POSITIVE LOGITS
    -shaped
    0.15
     Duty
    0.14
    ιÏĥ
    0.14
    DataTask
    0.14
    its
    0.14
    utf
    0.14
     ratt
    0.14
    anki
    0.14
    å½¢
    0.14
     Magazine
    0.14
    Activations Density 0.014%

    No Known Activations