INDEX

Explanations

possessive pronouns and associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

eil

-0.15

zon

-0.14

ible

-0.14

ç¨ĭåº¦

-0.14

æ»ħ

-0.13

ATABASE

-0.13

ç·ł

-0.13

ipel

-0.13

ockey

-0.13

ä¹

-0.13

POSITIVE LOGITS

 element

0.25

 appointed

0.22

 Element

0.21

 natural

0.19

 stride

0.19

 senses

0.18

Element

0.18

 accustomed

0.18

 true

0.18

 glory

0.18

Activations Density 0.094%

possessive pronouns and associated contexts

No Comments

No Known Activations