INDEX

Explanations

references to publication dates and historical timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

icari

-0.15

Nes

-0.15

"]."

-0.15

 Westbrook

-0.14

@}

-0.14

antro

-0.14

 prop

-0.14

erot

-0.13

weise

-0.13

ofday

-0.13

POSITIVE LOGITS

Ø¬Ø§Ø¯

0.16

itches

0.15

.usermodel

0.15

0.14

é«ĺæ¸ħ

0.14

ohon

0.14

 Lage

0.14

ask

0.14

unken

0.13

zÅĳ

0.13

Activations Density 0.053%

references to publication dates and historical timelines

No Comments

No Known Activations