INDEX

Explanations

timestamps and numerical data related to incidents or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 yere

-0.15

 wrought

-0.14

uses

-0.14

rights

-0.14

Ð¸Ð½ÐºÑĥ

-0.14

verage

-0.13

è¥

-0.13

gre

-0.13

pirit

-0.13

un

-0.13

POSITIVE LOGITS

ubb

0.17

ekl

0.16

emek

0.15

 Olsen

0.15

orre

0.15

acket

0.15

notated

0.14

 YÃ¼z

0.14

ibox

0.14

STA

0.14

Activations Density 0.067%

timestamps and numerical data related to incidents or events

No Comments

No Known Activations