INDEX

Explanations

instances of high-complexity interactions and significant actions in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 legacy

-0.17

legacy

-0.16

Printf

-0.14

_COMPILER

-0.14

à¸¸à¹ī

-0.14

 Legacy

-0.14

isko

-0.14

áº¡c

-0.14

ocale

-0.14

POSITIVE LOGITS

DEX

0.15

Band

0.15

icia

0.15

:init

0.15

 Band

0.15

èī²

0.14

ç©´

0.14

ede

0.14

\Url

0.14

Activations Density 0.020%

instances of high-complexity interactions and significant actions in narratives

No Comments

No Known Activations