© 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. 28-LLAMASCOPE-RES-32K
    11. 23385
    Prev
    Next
    INDEX
    Explanations

    historical references and evaluations related to music, specifically regarding Beethoven's work and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     должна
    -0.28
     бÑĭла
    -0.28
     ÑģÑĤала
    -0.27
     titul
    -0.26
     españ
    -0.23
     herself
    -0.23
     italiana
    -0.22
     utiliz
    -0.21
     envi
    -0.21
     ráp
    -0.21
    POSITIVE LOGITS
    ificado
    0.30
    ido
    0.30
    edido
    0.28
    erto
    0.28
    ativo
    0.28
    izzato
    0.28
    ulado
    0.28
    rido
    0.28
    ocado
    0.28
    gado
    0.28
    Activations Density 0.116%

    No Known Activations