INDEX

Explanations

references to individuals and their characteristics or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 ØŃÙĪ

-0.16

imes

-0.15

uest

-0.14

aks

-0.14

olley

-0.14

¶Į

-0.14

yn

-0.14

atel

-0.14

ì§

-0.13

ieri

-0.13

POSITIVE LOGITS

 with

0.15

>:</

0.14

rell

0.14

shan

0.14

 nothing

0.14

silver

0.14

 Pond

0.14

liner

0.14

bard

0.14

Ð½Ð¾Ð²

0.13

Activations Density 0.167%

references to individuals and their characteristics or actions

No Comments

No Known Activations