INDEX

Explanations

proper nouns, particularly names of people and places

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

kontakte

-0.17

inus

-0.16

ActivityResult

-0.15

atus

-0.14

loquent

-0.14

ture

-0.14

emu

-0.14

oldt

-0.14

tick

-0.13

ÐµÐ½ÑĤÐ°

-0.13

POSITIVE LOGITS

opoulos

0.33

ou

0.28

akis

0.28

Pap

0.27

outs

0.26

ourg

0.26

oul

0.26

tou

0.25

iou

0.25

atos

0.24

Activations Density 0.048%

proper nouns, particularly names of people and places

No Comments

No Known Activations