© 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. 15-LLAMASCOPE-RES-32K
    11. 2358
    Prev
    Next
    INDEX
    Explanations

    terms related to forms of support or refuge, particularly in the context of shelters and fostering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    portun
    -0.17
    erna
    -0.15
    earch
    -0.15
     latter
    -0.15
    istry
    -0.15
    cen
    -0.14
    Fatal
    -0.14
    acher
    -0.14
    yar
    -0.14
    ulo
    -0.14
    POSITIVE LOGITS
    ed
    0.40
    ing
    0.30
    edBy
    0.27
    edImage
    0.25
    edn
    0.24
    ë§ģ
    0.23
    edReader
    0.22
    edTextBox
    0.20
    izer
    0.20
    ize
    0.20
    Activations Density 0.141%

    No Known Activations