INDEX

Explanations

negations and words that indicate lack or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

znam

-0.16

lys

-0.14

arkin

-0.14

 spared

-0.14

Ð¾ÑĤÑĥ

-0.14

plete

-0.13

rello

-0.13

intel

-0.13

htub

-0.13

POSITIVE LOGITS

 DISCLAIM

0.19

.scalablytyped

0.18

oha

0.17

AtA

0.16

.AutoComplete

0.16

keh

0.15

cki

0.14

asi

0.14

igin

0.14

pod

0.14

Activations Density 0.096%

negations and words that indicate lack or absence

No Comments

No Known Activations