INDEX

Explanations

food-related terms and preparation instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 PVOID

-0.19

Ð»Ð°Ð´Ñĥ

-0.16

åŃĺæ¡£

-0.15

 Panc

-0.15

cene

-0.15

rix

-0.15

EIF

-0.14

ancellable

-0.14

 insp

-0.14

ucker

-0.14

POSITIVE LOGITS

lip

0.16

ylie

0.15

 stations

0.15

ä½³

0.15

Lip

0.15

elier

0.15

ìłĦ

0.14

 spread

0.14

 station

0.14

 graz

0.14

Activations Density 0.075%

food-related terms and preparation instructions

No Comments

No Known Activations