INDEX

Explanations

references to locations and positions in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

dorf

-0.14

ihar

-0.14

(anchor

-0.14

paque

-0.14

odash

-0.14

 Communities

-0.14

elight

-0.13

ettel

-0.13

 anch

-0.13

cko

-0.13

POSITIVE LOGITS

 stil

0.24

 Route

0.22

 route

0.19

-route

0.17

 barg

0.16

Route

0.16

tae

0.16

Ø¢ÙħØ¯

0.16

top

0.15

 Plot

0.15

Activations Density 0.145%

references to locations and positions in descriptions

No Comments

No Known Activations