INDEX

Explanations

significant numerical identifiers or values in data contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

arness

-0.14

opr

-0.14

oom

-0.14

 Mention

-0.13

adr

-0.13

_Syntax

-0.13

 Ð¿ÑĢÐ¸Ð²Ð¾Ð´

-0.12

/dd

-0.12

 Readers

-0.12

OU

-0.12

POSITIVE LOGITS

Ð¾Ð¶ÐµÑĤ

0.19

aires

0.15

eteria

0.15

vida

0.15

ssp

0.14

phin

0.14

vais

0.14

hift

0.13

uten

0.13

elow

0.13

Activations Density 0.014%

significant numerical identifiers or values in data contexts

No Comments

No Known Activations