INDEX

Explanations

cooking instructions and related culinary terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ieÅ¼

-0.16

 sometimes

-0.15

Tub

-0.14

alat

-0.14

ard

-0.14

sometimes

-0.14

iedo

-0.14

iek

-0.13

 moments

-0.13

dip

-0.13

POSITIVE LOGITS

uzzi

0.20

ìĽĶë¶ĢíĦ°

0.15

OUCH

0.15

eam

0.15

igo

0.14

weg

0.14

ebi

0.14

wi

0.14

rot

0.14

enko

0.14

Activations Density 0.024%

cooking instructions and related culinary terms

No Comments

No Known Activations