INDEX

Explanations

punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

::$_

-0.16

olia

-0.15

itar

-0.14

 Richmond

-0.14

ollen

-0.14

band

-0.14

QM

-0.14

unden

-0.13

iddles

-0.13

åľ

-0.13

POSITIVE LOGITS

rou

0.15

INLINE

0.15

EFR

0.15

ENDER

0.15

eneg

0.14

edException

0.14

andard

0.14

embros

0.14

elder

0.14

ologi

0.14

Activations Density 0.451%

punctuation marks

No Comments

No Known Activations