INDEX

Explanations

references to "all" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

undan

-0.16

stime

-0.15

agem

-0.15

Ð½Ð³

-0.14

ankan

-0.14

ontent

-0.14

ulares

-0.14

sla

-0.14

ular

-0.13

ispers

-0.13

POSITIVE LOGITS

 pace

0.18

0.16

iances

0.16

usion

0.16

iston

0.15

otre

0.15

nam

0.15

Checksum

0.15

erton

0.15

ouch

0.14

Activations Density 0.087%

references to "all" in various contexts

No Comments

No Known Activations