INDEX

Explanations

phrases related to interactions, communications, and processes involving people

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

uges

-0.16

sled

-0.15

enÃŃ

-0.15

ensa

-0.15

 parm

-0.13

assen

-0.13

issance

-0.13

ieg

-0.13

ares

-0.13

agna

-0.13

POSITIVE LOGITS

ings

0.18

 Tavern

0.15

INGS

0.15

Ø§ÙĩØ§

0.14

Tao

0.14

 checkpoint

0.14

çĶ

0.14

ets

0.14

ette

0.14

 Cult

0.14

Activations Density 0.172%

phrases related to interactions, communications, and processes involving people

No Known Activations