© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 20693
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of incompleteness or deficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utto
    -0.14
    ä¸ĭåİ»
    -0.14
    ignKey
    -0.14
    ảng
    -0.13
    _QUAL
    -0.13
    ecial
    -0.13
    ä¸įè¿ĩ
    -0.13
    ụy
    -0.13
    mq
    -0.13
     пÑĢавда
    -0.12
    POSITIVE LOGITS
     yet
    1.66
    yet
    1.45
     Yet
    1.30
    Yet
    1.25
     еÑīе
    0.59
     еÑīÑij
    0.57
     jeszcze
    0.55
     Ñīе
    0.52
     ancora
    0.51
    ãģ¾ãģł
    0.51
    Activations Density 0.442%

    No Known Activations