INDEX

Explanations

references to numerical data and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

sten

-0.17

sector

-0.16

opot

-0.15

 Furn

-0.15

 Tall

-0.15

resas

-0.14

çľ¾

-0.14

 sector

-0.14

ers

-0.14

 Glow

-0.14

POSITIVE LOGITS

idente

0.16

 Blair

0.15

ãĥĺ

0.14

ÙĨØ§Ø¡

0.14

Ľå»º

0.14

ennen

0.14

imdi

0.14

esco

0.13

ardo

0.13

à¥įà¤

0.13

Activations Density 0.180%

references to numerical data and publication details

No Comments

No Known Activations