INDEX

Explanations

references to locations and contexts within legal and organizational settings

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

arte

-0.17

vu

-0.16

abis

-0.15

à¤°à¤¤

-0.15

olo

-0.14

omitempty

-0.14

dorf

-0.14

ovÃŃ

-0.14

velt

-0.14

avel

-0.14

POSITIVE LOGITS

ainless

0.16

ummy

0.15

.Chain

0.15

ores

0.14

appa

0.14

chain

0.14

zer

0.14

 loophole

0.13

_AUX

0.13

ìĹħ

0.13

Activations Density 0.401%

references to locations and contexts within legal and organizational settings

No Comments

No Known Activations