INDEX

Explanations

phrases that indicate the initiation of actions or careers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

era

-0.16

ERA

-0.15

yll

-0.15

TEM

-0.15

rol

-0.14

oca

-0.14

tac

-0.13

OfClass

-0.13

ecl

-0.13

/owl

-0.13

POSITIVE LOGITS

 life

0.17

anic

0.16

ÑĢÐ¾Ðº

0.15

 hayat

0.15

arters

0.15

Øª

0.15

 blogging

0.14

.IsNullOr

0.14

 frequent

0.14

Ú©Ùħ

0.14

Activations Density 0.038%

phrases that indicate the initiation of actions or careers

No Comments

No Known Activations