INDEX

Explanations

historical dates related to significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

elight

-0.16

usercontent

-0.15

ffen

-0.14

inger

-0.14

bble

-0.14

gren

-0.14

-0.13

 Wagner

-0.13

 rescue

-0.13

POSITIVE LOGITS

forge

0.16

 aggreg

0.15

ãĥ³ãĤ¹

0.14

_TRIANGLES

0.14

darwin

0.13

ibus

0.13

itom

0.13

rowse

0.13

ErrorException

0.13

{*}

0.13

Activations Density 0.019%

historical dates related to significant events

No Comments

No Known Activations