INDEX

Explanations

occurrences of the letter 'G' and variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

elman

-0.16

 totalPages

-0.16

ambi

-0.15

ayet

-0.15

æĮ¯ãĤĬ

-0.15

Likes

-0.15

Ã©gor

-0.15

azes

-0.15

elix

-0.14

CrLf

-0.14

POSITIVE LOGITS

op

0.19

hat

0.19

rame

0.17

ond

0.17

house

0.16

opal

0.16

udi

0.16

zb

0.16

ouri

0.15

oving

0.15

Activations Density 0.027%

occurrences of the letter 'G' and variations of it in different contexts

No Comments

No Known Activations