INDEX

Explanations

concepts related to positioning and arrangement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Kurd

-0.19

-0.15

MER

-0.15

inox

-0.15

igit

-0.15

coli

-0.15

éľ

-0.15

inki

-0.14

MUX

-0.14

ÙıØ±

-0.14

POSITIVE LOGITS

ODO

0.19

OLS

0.17

 Martin

0.16

mania

0.16

Man

0.16

 mana

0.16

ohn

0.15

man

0.15

Man

0.15

Activations Density 0.064%

concepts related to positioning and arrangement

No Comments

No Known Activations