INDEX

Explanations

references to notable individuals or historical figures in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.Framework

-0.17

Ì£

-0.17

\OptionsResolver

-0.16

gger

-0.15

_ALWAYS

-0.15

isko

-0.14

bilt

-0.14

èľľ

-0.14

\grid

-0.14

_DEFINED

-0.14

POSITIVE LOGITS

‘

0.17

0.16

 multi

0.15

str

0.15

“

0.14

 carry

0.14

 Ã¢

0.14

Âł

0.14

MD

0.14

Activations Density 0.041%

references to notable individuals or historical figures in a narrative context

No Comments

No Known Activations