© 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. 8718
    Prev
    Next
    INDEX
    Explanations

    instances of the sound "ah", particularly in dialogue or emotional expressions

    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
     cupid
    -0.15
    cctor
    -0.14
     Datensch
    -0.13
    .RightToLeft
    -0.13
    Selectable
    -0.13
    anova
    -0.13
    sto
    -0.12
    _definitions
    -0.12
    o
    -0.12
    lies
    -0.12
    POSITIVE LOGITS
    ians
    0.19
    ian
    0.18
    iana
    0.16
    ův
    0.15
    itmap
    0.14
    ynchronously
    0.14
    (sp
    0.14
    ãģıãĤĵ
    0.14
    mania
    0.13
    -vous
    0.13
    Activations Density 0.337%

    No Known Activations