INDEX

Explanations

references to exam questions and related educational resources

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

otal

-0.17

avir

-0.15

ROLS

-0.15

igaret

-0.15

Hol

-0.15

rael

-0.14

 verde

-0.14

 Collapse

-0.14

 wonders

-0.13

Hol

-0.13

POSITIVE LOGITS

anzeigen

0.18

enes

0.16

expo

0.15

uju

0.14

core

0.14

åĨł

0.14

 (*((

0.14

eness

0.14

ecure

0.14

ekim

0.14

Activations Density 0.219%

references to exam questions and related educational resources

No Comments

No Known Activations