INDEX

Explanations

references to foreign involvement in various contexts

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

ARN

-0.15

*(*

-0.15

ritos

-0.15

errno

-0.14

ekl

-0.14

 XPAR

-0.14

grams

-0.14

 Ground

-0.13

 forged

-0.13

ripe

-0.13

POSITIVE LOGITS

igm

0.17

ieu

0.16

EDGE

0.15

eday

0.15

iou

0.15

æĮĻ

0.14

slu

0.14

vvm

0.14

ÑħÐ¾

0.14

 Sylv

0.14

Activations Density 0.037%

references to foreign involvement in various contexts

No Comments

No Known Activations

references to foreign involvement in various contexts

No Comments

No Known Activations