INDEX

Explanations

elements that indicate a discussion about structure and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ovsky

-0.18

AGR

-0.16

lis

-0.15

 Marino

-0.14

.dense

-0.14

erif

-0.14

UDGE

-0.14

çķª

-0.14

ellig

-0.14

CLUDING

-0.14

POSITIVE LOGITS

rient

0.17

orig

0.14

ais

0.14

 enough

0.14

andler

0.13

obec

0.13

orget

0.13

Î®

0.13

inya

0.13

urator

0.13

Activations Density 0.350%

elements that indicate a discussion about structure and organization

No Comments

No Known Activations