INDEX

Explanations

keywords related to categorization and evaluation 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Hog

-0.16

cplusplus

-0.15

ishi

-0.15

scar

-0.15

UGHT

-0.14

_ROUT

-0.14

Argb

-0.14

zew

-0.14

pie

-0.14

rch

-0.14

POSITIVE LOGITS

Ð²Ð°Ð´

0.17

antu

0.16

andi

0.15

val

0.15

erer

0.14

arrera

0.14

ãĥ³ãĥī

0.14

 subsid

0.14

 nond

0.14

Activations Density 0.002%

keywords related to categorization and evaluation in various contexts

No Comments

No Known Activations