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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 6567
    Prev
    Next
    INDEX
    Explanations

    elements related to cleverness or intelligence, particularly in language and writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hand
    -0.24
    ho
    -0.21
    hide
    -0.20
    hold
    -0.20
    haft
    -0.20
    erif
    -0.20
    hood
    -0.19
    hip
    -0.19
    hol
    -0.19
    hit
    -0.19
    POSITIVE LOGITS
    ting
    0.60
    ted
    0.44
    ters
    0.38
    tings
    0.37
    TING
    0.34
    ten
    0.30
    tingham
    0.28
    ãģĬãĤĬ
    0.28
    ropolis
    0.27
    tle
    0.25
    Activations Density 1.004%

    No Known Activations