INDEX

Explanations

times and locations referenced in a global context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ã§ak

-0.17

arry

-0.16

atalog

-0.15

áº¡ch

-0.15

-0.14

ÑĪÐ¸Ð±

-0.14

nell

-0.14

ircuit

-0.14

Ã¡Äį

-0.14

 Koch

-0.13

POSITIVE LOGITS

DST

0.19

 clocks

0.18

 fuels

0.17

Fu

0.17

uyo

0.17

_DST

0.16

 spring

0.15

sav

0.15

 Clock

0.15

umber

0.15

Activations Density 0.030%

times and locations referenced in a global context

No Comments

No Known Activations