INDEX

Explanations

punctuation marks, particularly exclamation points and periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uil

-0.17

versation

-0.17

Locator

-0.17

utin

-0.15

rais

-0.14

lsi

-0.14

locator

-0.14

 Meaning

-0.13

_derivative

-0.13

 Millenn

-0.13

POSITIVE LOGITS

Dit

0.18

eren

0.17

olio

0.16

ober

0.15

AFX

0.15

zer

0.15

å§«

0.15

Äįem

0.15

CRET

0.14

 æħ

0.14

Activations Density 0.024%

punctuation marks, particularly exclamation points and periods

No Comments

No Known Activations