INDEX

Explanations

elements related to corrections or references in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

å®ĺ

-0.15

nero

-0.15

aid

-0.14

ÑĪÐ¸Ð±

-0.13

Mus

-0.13

 ANAL

-0.13

 insan

-0.13

mus

-0.13

zab

-0.13

 Trib

-0.13

POSITIVE LOGITS

wake

0.15

etooth

0.15

eme

0.15

uden

0.14

 wake

0.14

 LÃª

0.14

ëĵ

0.14

.reflect

0.13

-Clause

0.13

bah

0.13

Activations Density 0.121%

elements related to corrections or references in writing

No Comments

No Known Activations