INDEX

Explanations

addresses and location details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

-0.15

cott

-0.15

leanup

-0.15

pan

-0.14

reference

-0.14

asje

-0.13

POSITIVE LOGITS

oord

0.14

ephy

0.13

ãĥ¼ãĥī

0.13

æ¤į

0.13

Rat

0.13

(EX

0.13

oin

0.13

isor

0.13

rah

0.13

ÏĦÎ¿Îº

0.13

Activations Density 0.065%

addresses and location details

No Comments

No Known Activations