INDEX

Explanations

instances of the word "One" and related variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

rene

-0.17

lich

-0.16

sc

-0.16

Ã¼ss

-0.15

sm

-0.15

ane

-0.14

 gratuita

-0.14

thora

-0.14

 ÙĨØ³Ø¨

-0.14

anean

-0.14

POSITIVE LOGITS

onta

0.26

idas

0.21

IDA

0.19

Fle

0.18

 Direction

0.18

ida

0.18

echan

0.17

Drive

0.17

ToOne

0.16

Republic

0.16

Activations Density 0.025%

instances of the word "One" and related variations

No Comments

No Known Activations