Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 2727
    Prev
    Next
    INDEX
    Explanations

    expressions of high praise or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sha
    -0.21
    sworth
    -0.17
    sj
    -0.16
    shi
    -0.16
    sh
    -0.15
    set
    -0.15
    sic
    -0.15
    sWith
    -0.15
    shan
    -0.15
    tridge
    -0.15
    POSITIVE LOGITS
    stit
    0.27
    iors
    0.25
    charged
    0.24
    lat
    0.24
    powers
    0.21
    human
    0.20
    stars
    0.20
    ior
    0.20
    cil
    0.19
    cedes
    0.19
    Activations Density 0.014%

    No Known Activations