INDEX

Explanations

references to editorial actions or annotations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

HECK

-0.15

orta

-0.14

ithe

-0.14

Hip

-0.14

à¸ĩà¸²à¸Ļ

-0.14

Severity

-0.14

Ham

-0.14

puter

-0.13

íĥ

-0.13

POSITIVE LOGITS

 Squadron

0.14

/schema

0.14

xeb

0.14

ÙĤÙĪÙĦ

0.14

rip

0.14

 Scheme

0.14

à¤²à¤¤

0.13

 fiat

0.13

 ÐĲÐ½Ð´

0.13

ieres

0.13

Activations Density 0.004%

references to editorial actions or annotations in text

No Comments

No Known Activations