INDEX

Explanations

phrases indicating acknowledgment of setbacks or negative circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

udur

-0.16

ISIBLE

-0.15

reme

-0.14

anou

-0.14

ropol

-0.14

Äĵ

-0.13

ãĤħ

-0.13

ouve

-0.13

venge

-0.13

Ð»ÑĥÐ±

-0.13

POSITIVE LOGITS

enden

0.15

wich

0.15

fac

0.15

lya

0.14

ellers

0.14

pis

0.14

 Rockefeller

0.14

aign

0.14

tail

0.14

 column

0.13

Activations Density 0.073%

phrases indicating acknowledgment of setbacks or negative circumstances

No Comments

No Known Activations