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. 27-LLAMASCOPE-RES-32K
    6. 11866
    Prev
    Next
    INDEX
    Explanations

    concepts related to organization and management tasks

    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
    ži
    -0.16
    Äĵ
    -0.16
     theres
    -0.14
    laz
    -0.14
     ï
    -0.14
    -ing
    -0.14
    éal
    -0.14
    ListGroup
    -0.14
    âĢij
    -0.14
    ç¯
    -0.14
    POSITIVE LOGITS
    oen
    0.18
    âĢĮ
    0.18
     te
    0.18
    oe
    0.17
    ait
    0.16
    ople
    0.16
    .dd
    0.16
    ίοÏĤ
    0.16
    t
    0.16
    âĢĮâĢĮ
    0.16
    Activations Density 0.832%

    No Known Activations