INDEX

Explanations

words related to the concept of "stand" or performance settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

å¼¾

-0.18

lope

-0.17

elman

-0.17

ptal

-0.16

ãĥ¼ãĤ¯

-0.16

asso

-0.15

ctic

-0.15

aki

-0.15

IRCLE

-0.15

ongyang

-0.14

POSITIVE LOGITS

urt

0.15

reau

0.15

 Picker

0.15

pread

0.15

 Spect

0.15

ÐµÐ½Ð¸

0.14

-alone

0.14

rÃ¡n

0.14

ings

0.14

ativnÃŃ

0.14

Activations Density 0.015%

words related to the concept of "stand" or performance settings

No Comments

No Known Activations