INDEX

Explanations

references to specific food names or dishes

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

athed

-0.16

enu

-0.15

ãģªãģĮãĤī

-0.15

loggedin

-0.15

ennes

-0.14

argas

-0.14

earn

-0.14

 Norte

-0.14

ened

-0.14

arbon

-0.14

POSITIVE LOGITS

-span

0.15

.cfg

0.15

efs

0.15

 latter

0.15

Macro

0.14

 clocks

0.14

ÏĥÏĥ

0.14

Î´Î®

0.13

 Macro

0.13

oning

0.13

Activations Density 0.024%

references to specific food names or dishes

No Comments

No Known Activations