INDEX

Explanations

instances and expressions related to finality or endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

abajo

-0.16

plan

-0.15

 onNext

-0.14

vsp

-0.14

äºĶæľĪ

-0.14

reet

-0.14

istar

-0.14

anova

-0.14

 nÃ¤ch

-0.13

LANGUAGE

-0.13

POSITIVE LOGITS

 before

0.34

before

0.27

 Before

0.26

 remaining

0.26

-before

0.25

Before

0.24

_before

0.24

remaining

0.24

 antes

0.23

 Remaining

0.23

Activations Density 0.114%

instances and expressions related to finality or endings

No Comments

No Known Activations