INDEX

Explanations

mentions of large selections or varieties of products and services

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ides

-0.15

ViewItem

-0.15

 condu

-0.15

_KP

-0.14

ongyang

-0.14

ennent

-0.14

 èĩ

-0.13

Ð¼ÐµÑĩ

-0.13

IMS

-0.13

uzzi

-0.13

POSITIVE LOGITS

 selection

0.56

 range

0.44

selection

0.43

 wide

0.43

 selections

0.42

 Selection

0.41

-selection

0.39

 sele

0.39

Selection

0.38

 choice

0.37

Activations Density 0.125%

mentions of large selections or varieties of products and services

No Comments

No Known Activations