INDEX

Explanations

references to "side," particularly in relation to cutting or positioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

maal

-0.20

 underlying

-0.16

erras

-0.15

lied

-0.15

OrNull

-0.14

cheid

-0.14

thing

-0.14

inkel

-0.14

ikh

-0.13

fts

-0.13

POSITIVE LOGITS

kick

0.23

(side

0.19

jÅ¡ÃŃ

0.17

 side

0.16

.Side

0.16

åī¯

0.15

ATALOG

0.15

reet

0.15

ploy

0.15

 sides

0.15

Activations Density 0.020%

references to "side," particularly in relation to cutting or positioning

No Comments

No Known Activations