INDEX

Explanations

references to challenges and problems

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

'gc

-0.16

udson

-0.15

ilinx

-0.15

XE

-0.15

ourg

-0.15

wine

-0.15

dek

-0.14

ignon

-0.14

 Oaks

-0.14

ØŃÙĩ

-0.14

POSITIVE LOGITS

 problem

0.16

Difficulty

0.15

Hoy

0.14

 Funding

0.14

enz

0.14

 Situation

0.14

Activations Density 0.127%

references to challenges and problems

No Comments

No Known Activations