INDEX

Explanations

mentions of regulatory agencies and food-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

oku

-0.17

ç§Ģ

-0.17

asca

-0.17

ndon

-0.16

imento

-0.16

 Ekon

-0.16

illon

-0.15

ieee

-0.15

ekim

-0.14

TES

-0.14

POSITIVE LOGITS

-to

0.17

stal

0.16

ky

0.15

hang

0.15

hol

0.15

consts

0.15

 âĨĲ

0.14

-K

0.14

UPS

0.14

ols

0.14

Activations Density 0.052%

mentions of regulatory agencies and food-related terms

No Comments

No Known Activations