INDEX

Explanations

phrases indicating reluctance or negative sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bie

-0.16

arget

-0.15

hl

-0.15

chor

-0.15

******/

-0.14

 Wich

-0.14

Ð¾ÑĢÑĥ

-0.14

atu

-0.14

izon

-0.14

POSITIVE LOGITS

FO

0.15

StdString

0.15

ÏģÎ·

0.14

 sweep

0.14

etÃŃ

0.14

.sdk

0.14

ulaÃ§Ã£o

0.13

á»ĭnh

0.13

onian

0.13

cm

0.13

Activations Density 0.437%

phrases indicating reluctance or negative sentiment

No Comments

No Known Activations