INDEX

Explanations

negative statements or negations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

aggi

-0.16

rees

-0.14

 ÐľÑĸÐ½ÑĸÑģÑĤÐµÑĢ

-0.14

çıł

-0.14

etic

-0.13

MMI

-0.13

ettel

-0.13

.Module

-0.13

.stamp

-0.13

 rejo

-0.13

POSITIVE LOGITS

landers

0.15

ubo

0.14

lander

0.14

 DÃ¼z

0.14

pard

0.14

 Trit

0.14

Ð¾Ð¿Ð¾Ð»

0.14

auge

0.14

çĪ½

0.13

aqu

0.13

Activations Density 0.001%

negative statements or negations

No Comments

No Known Activations