INDEX

Explanations

emotional adjectives related to experiences that are both positive and negative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.17

zan

-0.16

ypse

-0.15

ondon

-0.14

 fittings

-0.14

RIES

-0.14

oyer

-0.14

ries

-0.13

POSITIVE LOGITS

ly

0.40

LY

0.23

ÑģÑı

0.23

ingly

0.21

redients

0.19

redient

0.18

hausen

0.17

gg

0.16

åĻ¨

0.16

lys

0.16

Activations Density 0.124%

emotional adjectives related to experiences that are both positive and negative

No Comments

No Known Activations