INDEX

Explanations

references to commitments and decisions regarding actions or responsibilities

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

jong

-0.17

 support

-0.16

 Opposition

-0.16

-support

-0.15

onda

-0.14

 fork

-0.14

 Saud

-0.14

 Support

-0.14

zag

-0.14

 wrong

-0.14

POSITIVE LOGITS

swer

0.16

elah

0.16

´Ģ

0.16

 Weiner

0.14

ilere

0.13

.hom

0.13

_lifetime

0.13

ìĽĮ

0.13

loating

0.13

Spo

0.13

Activations Density 0.231%

references to commitments and decisions regarding actions or responsibilities

No Comments

No Known Activations