INDEX

Explanations

phrases indicating conditional or situational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

axon

-0.15

xing

-0.15

(strict

-0.15

à¤ķà¤¨

-0.15

akis

-0.15

Ð°Ð»Ð¾Ð²

-0.14

ROSS

-0.14

ÙĦÙĬÙĩ

-0.14

alu

-0.14

ongan

-0.13

POSITIVE LOGITS

 chances

0.15

 stands

0.15

standing

0.15

 Guerr

0.15

 Active

0.15

Stand

0.14

 subrange

0.14

Active

0.14

 Stand

0.14

 stand

0.14

Activations Density 0.010%

phrases indicating conditional or situational contexts

No Comments

No Known Activations