INDEX

Explanations

words related to knitting and knitted products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

åĭ¤

-0.16

les

-0.15

-ÑĤÐ¾

-0.15

erti

-0.15

otec

-0.15

als

-0.15

Ð·Ð½Ð°Ñĩ

-0.14

amat

-0.14

aeda

-0.14

POSITIVE LOGITS

inery

0.16

owel

0.15

isia

0.15

inos

0.15

ullah

0.15

éĻĲ

0.14

upy

0.14

udas

0.14

omen

0.14

istring

0.14

Activations Density 0.005%

words related to knitting and knitted products

No Comments

No Known Activations