INDEX

Explanations

specific occurrences of the letter 'g' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ambi

-0.17

argent

-0.16

ÅĻÃŃz

-0.15

ting

-0.15

inger

-0.15

 Trout

-0.15

chaft

-0.15

old

-0.15

.mx

-0.14

 Ð¿Ð¾Ð´ÑħÐ¾Ð´

-0.14

POSITIVE LOGITS

 dying

0.15

 indu

0.14

usher

0.14

æ·±

0.14

Hd

0.14

Ð¼Ñĭ

0.14

ubo

0.14

vard

0.14

ãĤ¸ãĥ¥

0.13

 deep

0.13

Activations Density 0.017%

specific occurrences of the letter 'g' in various contexts

No Comments

No Known Activations