INDEX

Explanations

specific names and titles associated with various entities or works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

orners

-0.15

indow

-0.15

jin

-0.14

ottom

-0.14

ÑĶÐ¼

-0.14

urs

-0.14

å¸¯

-0.13

ichten

-0.13

rof

-0.13

 Fork

-0.13

POSITIVE LOGITS

Ã©li

0.15

acos

0.15

[|

0.15

wort

0.14

gro

0.13

 Kirby

0.13

erken

0.13

_DEN

0.13

Counter

0.13

 Ð³Ð»Ð¸

0.13

Activations Density 0.226%

specific names and titles associated with various entities or works

No Comments

No Known Activations