INDEX

Explanations

instances of the word "imagine" and its variations related to envisioning or conceptualizing ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

age

-0.20

ÐµÐ½Ð·

-0.16

IBUT

-0.15

ammable

-0.15

rega

-0.14

lfw

-0.14

å¤

-0.14

ylie

-0.14

chan

-0.14

played

-0.14

POSITIVE LOGITS

agine

0.17

ering

0.16

 ÑģÐ¾Ð±Ñĸ

0.16

_INLINE

0.15

ered

0.15

 leap

0.15

ilib

0.15

aries

0.15

erde

0.15

ined

0.14

Activations Density 0.018%

instances of the word "imagine" and its variations related to envisioning or conceptualizing ideas

No Comments

No Known Activations