INDEX

Explanations

references to outer or exterior elements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iba

-0.21

zilla

-0.16

ietet

-0.15

 fever

-0.15

lej

-0.15

AVIS

-0.15

lik

-0.14

ertext

-0.14

ule

-0.14

ObjectContext

-0.14

POSITIVE LOGITS

most

0.20

 outside

0.18

outside

0.18

 Outside

0.18

Outside

0.17

-most

0.17

adem

0.16

TERNAL

0.16

ãĥ³ãĥĳ

0.15

ternal

0.15

Activations Density 0.046%

references to outer or exterior elements

No Comments

No Known Activations