INDEX

Explanations

specific names and titles related to literature or media

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

-0.15

éĺª

-0.13

occo

-0.13

éĻħ

-0.13

 OnCollision

-0.12

cou

-0.12

itr

-0.12

ILLS

-0.12

ãģ¨ãģĵãĤį

-0.12

POSITIVE LOGITS

Uhr

0.14

orn

0.14

 yans

0.14

Ø°ÙĬ

0.14

enegro

0.14

/frontend

0.13

ledon

0.13

CEE

0.13

upert

0.13

tober

0.13

Activations Density 0.293%

specific names and titles related to literature or media

No Comments

No Known Activations