INDEX

Explanations

annotations and overridden methods in code

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

UnderTest

-0.17

IVAL

-0.14

 ########.

-0.14

 phim

-0.14

Ø±ÙĬØ¯

-0.14

[at

-0.14

Scoped

-0.14

rette

-0.13

zee

-0.13

.retrieve

-0.13

POSITIVE LOGITS

uly

0.15

ippo

0.14

unting

0.14

.proto

0.14

ope

0.13

 Companion

0.13

kip

0.13

ACA

0.13

 companion

0.13

aca

0.12

Activations Density 0.020%

annotations and overridden methods in code

No Comments

No Known Activations