INDEX

Explanations

vocabulary related to provocation or thought-provoking concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bai

-0.17

ba

-0.16

 Solic

-0.15

 Fran

-0.14

utr

-0.14

vaz

-0.14

uco

-0.14

Ñİ

-0.14

istol

-0.14

POSITIVE LOGITS

çĿ

0.18

soever

0.17

ColumnType

0.17

Bindable

0.15

/downloads

0.15

xs

0.15

ollar

0.14

ell

0.14

agr

0.14

 Reef

0.14

Activations Density 0.026%

vocabulary related to provocation or thought-provoking concepts

No Comments

No Known Activations