INDEX

Explanations

key phrases and punctuation that indicate a narrative or storytelling structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

iros

-0.16

GR

-0.15

ssi

-0.15

 scoreboard

-0.14

attro

-0.14

compass

-0.14

ÐĴÐĲ

-0.14

orer

-0.14

erse

-0.14

POSITIVE LOGITS

aily

0.18

FormField

0.15

awi

0.15

aura

0.15

0.14

uther

0.14

å½¢æĪĲ

0.14

zier

0.14

_STD

0.14

 Bernard

0.14

Activations Density 0.001%

key phrases and punctuation that indicate a narrative or storytelling structure

No Comments

No Known Activations