INDEX

Explanations

instances of the word "align" and its variations, indicating a focus on concepts of alignment and agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elyn

-0.19

Ø®Ø§ÙĨÙĩ

-0.17

zk

-0.17

 láº¡i

-0.17

à

-0.16

Ã¡nh

-0.16

els

-0.15

stown

-0.14

stral

-0.14

 Dá»¯

-0.14

POSITIVE LOGITS

arity

0.21

amenti

0.20

ments

0.20

 perfectly

0.18

ird

0.16

MENT

0.16

edly

0.16

ingly

0.16

EMENT

0.16

imenti

0.15

Activations Density 0.019%

instances of the word "align" and its variations, indicating a focus on concepts of alignment and agreement

No Comments

No Known Activations