INDEX

Explanations

phrases indicating states of being or conditions of the subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

rud

-0.16

loid

-0.15

enha

-0.15

ÑĦÐ¾ÑĢÑĤ

-0.15

 scopes

-0.15

onis

-0.14

isas

-0.14

isko

-0.14

oit

-0.13

opes

-0.13

POSITIVE LOGITS

0.15

achel

0.14

aller

0.14

GetType

0.14

ACHE

0.13

 absol

0.13

ych

0.13

Ø¶

0.13

æŁ´

0.13

Activations Density 0.048%

phrases indicating states of being or conditions of the subject

No Comments

No Known Activations