INDEX

Explanations

numerical data and statistics related to events or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rif

-0.17

ifest

-0.16

ugo

-0.15

 quali

-0.15

cola

-0.15

Ø±Ùī

-0.14

umin

-0.13

nge

-0.13

cmb

-0.13

Ø´Ø§Ø±

-0.13

POSITIVE LOGITS

apr

0.16

Ð°ÑĢÑĮ

0.16

urtles

0.15

-overlay

0.14

 kariy

0.14

gang

0.14

 cÃ´

0.14

Ms

0.14

uckle

0.13

.must

0.13

Activations Density 0.129%

numerical data and statistics related to events or rankings

No Comments

No Known Activations