INDEX

Explanations

references to visual perception and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÂĿ

-0.18

 ÑģÐ¾Ð±Ñĸ

-0.15

idious

-0.14

phans

-0.14

theid

-0.14

abstractmethod

-0.14

tractive

-0.13

-ÑĤÐ¾

-0.13

woke

-0.13

>(()

-0.13

POSITIVE LOGITS

cluding

0.25

chÃ©

0.21

ä¹İ

0.19

izando

0.18

ecause

0.18

halb

0.17

outu

0.17

à¸Ńà¸ĩà¸Īà¸²à¸ģ

0.17

etheless

0.17

lieÃŁlich

0.17

Activations Density 0.316%

references to visual perception and related concepts

No Comments

No Known Activations