INDEX

Explanations

numerical values related to measurements or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lesc

-0.16

ä¸ĸç´Ģ

-0.16

one

-0.16

ovo

-0.16

ovi

-0.16

opp

-0.15

coming

-0.15

oothing

-0.15

ceeded

-0.15

obel

-0.15

POSITIVE LOGITS

0.22

-ÑĤÐ¾

0.17

Éµ

0.17

0.16

ulan

0.15

à¥Ĥà¤¦

0.15

Configurer

0.15

ä¸»ç¾©

0.14

lei

0.14

Û°Û°Û°

0.14

Activations Density 0.126%

numerical values related to measurements or specifications

No Comments

No Known Activations