INDEX

Explanations

references to significant political figures and their roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aur

-0.16

ÂŃ

-0.14

 Perkins

-0.14

Æ¡

-0.13

 respectively

-0.13

icot

-0.13

’

-0.13

 âĢ¦↵

-0.12

POSITIVE LOGITS

 ifdef

0.15

peq

0.14

indle

0.14

aab

0.13

.shader

0.13

$MESS

0.13

ÑģÑĤÑĢÐ¾

0.13

nyder

0.13

.datatables

0.13

enler

0.13

Activations Density 0.266%

references to significant political figures and their roles or actions

No Comments

No Known Activations