INDEX

Explanations

references to taking leave or absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

tering

-0.17

ean

-0.15

 permanently

-0.15

unning

-0.14

-count

-0.14

esson

-0.14

ican

-0.14

ero

-0.14

ctica

-0.13

DEF

-0.13

POSITIVE LOGITS

atform

0.17

0.16

edriver

0.14

 intensive

0.14

raquo

0.14

anja

0.13

 doma

0.13

},{

0.13

oine

0.13

Activations Density 0.007%

references to taking leave or absence

No Comments

No Known Activations