INDEX

Explanations

code-related keywords and function definitions related to user management

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

pled

-0.16

indle

-0.15

oine

-0.15

punkt

-0.14

 Morg

-0.14

zano

-0.14

xbb

-0.14

pite

-0.14

uno

-0.14

POSITIVE LOGITS

ery

0.18

ERY

0.17

isure

0.15

ilogy

0.14

rones

0.14

çĬ¯

0.14

ç¸®

0.14

 Colony

0.13

ispers

0.13

athi

0.13

Activations Density 0.003%

code-related keywords and function definitions related to user management

No Comments

No Known Activations