INDEX

Explanations

expressions related to communication and interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

UGINS

-0.15

ÃĸL

-0.15

Ã¼gen

-0.15

 Astroph

-0.14

ynos

-0.14

ÑħÐ¾

-0.14

à¸Ļà¸Ń

-0.14

ë¡ľëĵľ

-0.14

IXEL

-0.14

POSITIVE LOGITS

ãĥĥãĥī

0.15

Via

0.15

atri

0.14

ults

0.14

via

0.14

INA

0.14

Chi

0.14

ipe

0.14

.opens

0.14

roz

0.14

Activations Density 0.030%

expressions related to communication and interaction

No Comments

No Known Activations