INDEX

Explanations

terms related to coordination and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

kÃ¶

-0.16

hall

-0.15

GINE

-0.15

Ã¼nd

-0.15

ìĿµ

-0.14

acter

-0.14

legg

-0.14

aller

-0.14

enda

-0.14

uf

-0.14

POSITIVE LOGITS

 efforts

0.19

eff

0.18

hea

0.18

 effort

0.18

cus

0.17

-eff

0.16

Eff

0.15

Ð¾ÑĢÐ¾Ð½

0.15

ondon

0.14

edly

0.14

Activations Density 0.015%

terms related to coordination and organization

No Comments

No Known Activations