INDEX

Explanations

references to individuals, particularly in terms of their influence or significance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ICE

-0.18

irm

-0.15

fern

-0.15

errer

-0.14

ICE

-0.14

mey

-0.14

arÃ¡

-0.13

leon

-0.13

orts

-0.13

æŀľ

-0.13

POSITIVE LOGITS

Ñī

0.17

ÙĦØ³ÙĦ

0.16

ilet

0.15

aire

0.15

dzi

0.14

ê²½

0.14

declspec

0.13

htag

0.13

 WINAPI

0.13

rary

0.13

Activations Density 0.045%

references to individuals, particularly in terms of their influence or significance

No Comments

No Known Activations