INDEX

Explanations

specific coding patterns or identifiers within technical or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ssp

-0.17

CCC

-0.15

opsy

-0.14

ptom

-0.14

isOk

-0.14

/OR

-0.14

.yahoo

-0.14

setError

-0.14

---</

-0.14

Ã¶ÃŁe

-0.13

POSITIVE LOGITS

EM

0.19

ID

0.19

IC

0.17

API

0.17

AS

0.17

IT

0.17

AM

0.16

US

0.16

antz

0.16

ZIP

0.16

Activations Density 0.120%

specific coding patterns or identifiers within technical or medical contexts

No Comments

No Known Activations