INDEX

Explanations

instances of personal pronouns and expressions of status or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÏĦÏį

-0.18

éľĩ

-0.15

ilon

-0.15

awe

-0.15

 reportedly

-0.15

 Apparently

-0.15

 apparently

-0.14

ÎŃ

-0.14

ymes

-0.14

 åı·

-0.14

POSITIVE LOGITS

 somehow

0.20

 stepped

0.20

 someone

0.19

 suddenly

0.17

 transported

0.16

loh

0.15

 váºŃy

0.15

 tele

0.15

 somebody

0.15

someone

0.15

Activations Density 0.149%

instances of personal pronouns and expressions of status or characteristics

No Comments

No Known Activations