INDEX

Explanations

terms related to specific actions or processes 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 VerfÃ¼g

-0.17

otts

-0.16

 sublic

-0.15

essim

-0.14

visible

-0.14

uhl

-0.14

 Steele

-0.14

olume

-0.14

 Ø£Ø¹ÙĦØ§Ùħ

-0.13

buah

-0.13

POSITIVE LOGITS

ame

0.15

unds

0.15

oki

0.15

áº¿t

0.15

Exc

0.14

hots

0.14

neck

0.14

claimer

0.14

exc

0.14

Bis

0.14

Activations Density 0.034%

terms related to specific actions or processes in various contexts

No Comments

No Known Activations