INDEX

Explanations

references to improvement or enhancement 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

afka

-0.15

.dtd

-0.15

-0.14

ecure

-0.14

pak

-0.14

byn

-0.14

pok

-0.14

etter

-0.13

ÏĢÏīÏĤ

-0.13

atar

-0.13

POSITIVE LOGITS

rollo

0.16

Äįka

0.15

ocio

0.15

orns

0.15

icha

0.15

uala

0.14

rophe

0.14

sing

0.14

ÑĢÐ¸ÑģÑĤÐ¸

0.14

olen

0.14

Activations Density 0.223%

references to improvement or enhancement in various contexts

No Comments

No Known Activations