INDEX

Explanations

references to issues and problems faced during experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

too

-0.18

Too

-0.17

Ø³ØªØ§ÙĨ

-0.17

lÃ¤

-0.16

too

-0.15

TOO

-0.15

Too

-0.15

ordin

-0.15

-too

-0.14

POSITIVE LOGITS

 seam

0.18

 looks

0.17

imes

0.16

nant

0.16

 Seam

0.16

 worth

0.15

 look

0.15

 Looks

0.15

Ã´

0.15

 happ

0.15

Activations Density 0.125%

references to issues and problems faced during experiences

No Comments

No Known Activations