INDEX

Explanations

references to third-party entities or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

acho

-0.20

ania

-0.16

ube

-0.14

pack

-0.14

obby

-0.14

ned

-0.14

avou

-0.14

chen

-0.14

le

-0.14

uento

-0.14

POSITIVE LOGITS

Zy

0.15

reff

0.15

muh

0.14

urtle

0.14

_cases

0.14

 Mayo

0.14

åĮ

0.14

çģ£

0.14

erez

0.13

Activations Density 0.017%

references to third-party entities or organizations

No Comments

No Known Activations