INDEX

Explanations

terms related to specific software and system configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

berger

-0.16

rance

-0.16

Î

-0.15

elow

-0.15

pter

-0.14

argin

-0.14

ehler

-0.14

inen

-0.14

hin

-0.13

:↵↵↵↵↵↵

-0.13

POSITIVE LOGITS

fat

0.15

erli

0.15

abox

0.15

Cab

0.15

VV

0.15

olumn

0.15

atted

0.14

ucz

0.14

uelle

0.14

fÃ¼g

0.14

Activations Density 0.025%

terms related to specific software and system configurations

No Comments

No Known Activations