INDEX

Explanations

phrases indicating positive outcomes or successful results from actions taken

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ints

-0.15

undred

-0.15

ENSITY

-0.14

@brief

-0.14

 componentDid

-0.14

yle

-0.14

_blob

-0.13

expired

-0.13

ecd

-0.13

llib

-0.13

POSITIVE LOGITS

 increased

0.21

 greater

0.19

 decreased

0.18

 further

0.16

an

0.15

 creation

0.15

 eventual

0.15

 widespread

0.14

 frequent

0.14

Activations Density 0.111%

phrases indicating positive outcomes or successful results from actions taken

No Comments

No Known Activations