INDEX

Explanations

references to military and legal accountability or actions

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

eld

-0.15

emoc

-0.15

Ø§ÙĦÙĩ

-0.14

estyle

-0.14

 stroj

-0.14

AAF

-0.14

midd

-0.14

leanup

-0.14

ë³ĳ

-0.13

 Wahl

-0.13

POSITIVE LOGITS

amac

0.17

 Bair

0.16

orum

0.15

 bytesRead

0.15

oka

0.15

 Compatibility

0.15

_compat

0.15

 convent

0.15

realloc

0.14

aders

0.14

Activations Density 0.030%

references to military and legal accountability or actions

No Comments

No Known Activations