INDEX

Explanations

phrases or descriptions involving physical attributes or actions of objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 appearances

-0.14

enter

-0.14

nnen

-0.14

rien

-0.14

ques

-0.14

 unint

-0.13

ult

-0.13

zew

-0.13

exp

-0.13

é»İ

-0.13

POSITIVE LOGITS

AllWindows

0.17

chu

0.15

attro

0.14

 intact

0.14

 jadx

0.14

ABCDE

0.14

WK

0.14

upe

0.13

.tp

0.13

_defaults

0.13

Activations Density 0.136%

phrases or descriptions involving physical attributes or actions of objects

No Comments

No Known Activations