INDEX

Explanations

deterministic phrases and elements related to specific quantities or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iÄįky

-0.15

ãĥĥãĥģ

-0.15

andel

-0.15

selection

-0.14

 Ø§ÙĦÙħØ¬

-0.14

rech

-0.14

 {{--<

-0.13

mite

-0.13

Jun

-0.13

 WaitForSeconds

-0.13

POSITIVE LOGITS

0.15

or

0.14

ienne

0.14

 Faker

0.14

oric

0.14

amin

0.14

iamond

0.14

ÑĢÐ¾Ñī

0.13

 previews

0.13

posable

0.13

Activations Density 0.014%

deterministic phrases and elements related to specific quantities or relationships

No Comments

No Known Activations