INDEX

Explanations

measurements and quantities in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

nore

-0.14

fid

-0.14

Fog

-0.14

.Sdk

-0.14

ancel

-0.14

hetto

-0.14

olk

-0.14

§

-0.14

áº¿t

-0.14

FI

-0.13

POSITIVE LOGITS

Ĥ

0.17

 leaf

0.15

leaf

0.15

 Cheney

0.14

á»©ng

0.14

lein

0.14

 fluid

0.14

Ä±ÅŁma

0.14

conds

0.14

iture

0.14

Activations Density 0.008%

measurements and quantities in recipes

No Comments

No Known Activations