INDEX

Explanations

references to the concept of matching in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ated

-0.16

Cyr

-0.16

 jsonResponse

-0.15

ury

-0.15

ike

-0.15

uckets

-0.15

hti

-0.14

ÑģÐ¸

-0.14

unu

-0.14

zie

-0.14

POSITIVE LOGITS

ingly

0.21

(es

0.18

DispatchToProps

0.16

riz

0.15

abile

0.15

_EXTERN

0.15

able

0.15

ipse

0.15

arel

0.15

-ups

0.14

Activations Density 0.062%

references to the concept of matching in various contexts

No Comments

No Known Activations