INDEX

Explanations

mentions of specific research methodologies or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

hti

-0.20

loon

-0.16

idlo

-0.14

fik

-0.14

ht

-0.14

Ð¾ÑĩÐºÐ°

-0.14

 gele

-0.14

_,

-0.14

ifica

-0.14

ivant

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.17

stein

0.15

lington

0.15

mod

0.15

#{@

0.14

stoi

0.14

Smy

0.14

ameda

0.14

STANCE

0.13

ioctl

0.13

Activations Density 0.047%

mentions of specific research methodologies or approaches

No Comments

No Known Activations