INDEX

Explanations

the presence of specific verbs and locations within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elsey

-0.18

adies

-0.17

itu

-0.16

beck

-0.16

orum

-0.16

ipa

-0.16

acro

-0.15

.RemoveAll

-0.15

esson

-0.14

OUNT

-0.14

POSITIVE LOGITS

 dikke

0.19

 Closed

0.18

sealed

0.17

 CLOSED

0.17

 closed

0.17

Secret

0.16

ibold

0.16

Closed

0.16

closed

0.15

isclosed

0.15

Activations Density 0.002%

the presence of specific verbs and locations within a text

No Comments

No Known Activations