INDEX

Explanations

phrases and actions related to providing information and instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

us

-0.23

/cop

-0.16

áº¯ng

-0.16

 Sheets

-0.15

us

-0.15

Tel

-0.15

 syslog

-0.14

mey

-0.14

 Stevenson

-0.14

 Exiting

-0.14

POSITIVE LOGITS

 ourselves

0.25

bsp

0.16

eded

0.16

unsch

0.15

ufen

0.15

plemented

0.14

insula

0.14

itches

0.14

gings

0.13

ertz

0.13

Activations Density 1.853%

phrases and actions related to providing information and instructions

No Comments

No Known Activations