INDEX

Explanations

expressions of consumer interest and positive feedback towards products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iform

-0.15

 prot

-0.15

 Ð¿ÑĢÐ¾ÑĤ

-0.14

ISTA

-0.14

ids

-0.14

grese

-0.14

 Prot

-0.14

 pall

-0.14

prot

-0.14

 Swords

-0.14

POSITIVE LOGITS

 Seed

0.15

ree

0.14

Î¸Î¼

0.14

 ÙĨÙĪÙģ

0.14

adil

0.14

peq

0.13

 Consolid

0.13

å¥ī

0.13

ehir

0.13

iets

0.13

Activations Density 0.009%

expressions of consumer interest and positive feedback towards products

No Comments

No Known Activations