INDEX

Explanations

instances of the word "or" and related phrases indicating choices or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

achuset

-0.15

APPER

-0.15

ARSE

-0.15

esseract

-0.15

-0.14

á»īnh

-0.14

akra

-0.14

 maxim

-0.14

PIT

-0.14

Ã¡h

-0.14

POSITIVE LOGITS

atore

0.16

wert

0.16

å¤©å¤©

0.15

unu

0.14

_Exception

0.14

 Timing

0.14

é¨

0.14

ator

0.14

ÆĴ

0.14

_thumb

0.13

Activations Density 0.025%

instances of the word "or" and related phrases indicating choices or alternatives

No Comments

No Known Activations