INDEX

Explanations

expressions indicating denial or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

dip

-0.17

 forg

-0.17

ugas

-0.16

emap

-0.16

Dip

-0.15

hem

-0.15

 Alam

-0.14

 Gang

-0.14

 nice

-0.14

onz

-0.14

POSITIVE LOGITS

Ã³nico

0.18

nodoc

0.17

iker

0.15

è¶Ĭ

0.15

FINITE

0.15

DownList

0.15

iotic

0.14

icer

0.14

éļł

0.14

iday

0.14

Activations Density 0.026%

expressions indicating denial or negation

No Comments

No Known Activations