INDEX

Explanations

sections of text that denote descriptions or summaries of items, services, or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ãģªãģĹ

-0.15

Î»Î¯

-0.14

hill

-0.14

velopment

-0.14

ÅĤo

-0.14

 McCabe

-0.14

 ÑģÐ¾ÑģÑĤÐ¾Ñı

-0.13

Î»Ïİ

-0.13

 Lage

-0.13

ectar

-0.13

POSITIVE LOGITS

 Bend

0.15

ç©¿

0.15

Aux

0.15

TED

0.14

urret

0.14

ValuePair

0.14

 auxiliary

0.14

 rendering

0.14

zza

0.14

ullen

0.14

Activations Density 0.001%

sections of text that denote descriptions or summaries of items, services, or events

No Comments

No Known Activations