INDEX

Explanations

phrases that express curiosity or a desire for information

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

occo

-0.16

hoe

-0.14

orting

-0.14

æŀ¶

-0.14

RITE

-0.14

oval

-0.14

 Hamm

-0.14

à¸·à¹ī

-0.14

enheim

-0.14

splice

-0.13

POSITIVE LOGITS

ãĥ¥

0.15

lod

0.14

ighest

0.14

 Nich

0.14

ÑĢÑıÐ´

0.14

Ã¡ÅĻe

0.14

inine

0.14

ÏĦÎ¿Î»

0.13

 Lodge

0.13

ull

0.13

Activations Density 0.033%

phrases that express curiosity or a desire for information

No Comments

No Known Activations