INDEX

Explanations

instances of the word "over" used 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ulously

-0.18

apesh

-0.16

Ã¼stÃ¼

-0.15

ensively

-0.15

lessly

-0.14

apÄ±

-0.14

Ã¡lt

-0.14

htable

-0.13

Ð¾Ð¿Ð°Ñģ

-0.13

oldur

-0.13

POSITIVE LOGITS

AGMENT

0.17

stub

0.15

nen

0.15

Ð¸ÑĤÐ¸

0.15

ness

0.14

nech

0.14

men

0.14

0.13

kin

0.13

most

0.13

Activations Density 0.104%

instances of the word "over" used in various contexts

No Comments

No Known Activations