INDEX

Explanations

repeated phrases and singular judgments or qualifying statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.18

 Technical

-0.15

iscal

-0.15

_pf

-0.14

 cort

-0.14

 Bernard

-0.14

.adv

-0.14

CRET

-0.14

bes

-0.14

 termin

-0.14

POSITIVE LOGITS

çĻºè¡¨

0.16

.getMinutes

0.14

aigned

0.14

TickCount

0.14

ertz

0.14

vor

0.14

hausen

0.14

Î³Î¿Ïħ

0.14

ÐµÐ½ÑĤÑĥ

0.14

rende

0.14

Activations Density 0.053%

repeated phrases and singular judgments or qualifying statements

No Comments

No Known Activations