© 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. 16-LLAMASCOPE-RES-32K
    11. 1899
    Prev
    Next
    INDEX
    Explanations

    words related to positive and negative experiences or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maar
    -0.15
    issant
    -0.14
    isis
    -0.14
    /XML
    -0.13
    ëį°
    -0.13
     componentDid
    -0.13
    ufe
    -0.13
    ries
    -0.13
    stance
    -0.13
    à¥ģà¤Ĺ
    -0.13
    POSITIVE LOGITS
     having
    0.15
    273
    0.15
    BoxLayout
    0.15
    VA
    0.15
    736
    0.14
    pace
    0.14
    143
    0.14
    631
    0.14
    548
    0.13
    iqueta
    0.13
    Activations Density 0.074%

    No Known Activations