INDEX

Explanations

references to tourist attractions and landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/topics

-0.17

.jp

-0.16

ython

-0.14

ãĥŃãĥ¼

-0.14

imientos

-0.14

efe

-0.14

yster

-0.14

 Sims

-0.13

rokes

-0.13

nown

-0.13

POSITIVE LOGITS

ghi

0.18

unca

0.15

JS

0.15

Subject

0.14

arna

0.14

frm

0.14

adel

0.13

pub

0.13

cy

0.13

Activations Density 0.004%

references to tourist attractions and landmarks

No Comments

No Known Activations