INDEX

Explanations

imperative phrases that encourage action or decision-making

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

riba

-0.17

annotations

-0.17

DSA

-0.15

ilty

-0.15

abled

-0.14

ovol

-0.14

affen

-0.13

uario

-0.13

æĬĺ

-0.13

 Canary

-0.13

POSITIVE LOGITS

ãĥ«ãĤ¯

0.17

Î¹ÎºÎ·

0.14

KBS

0.14

ANTA

0.14

 bast

0.14

 Jerome

0.14

Rut

0.14

 Barcl

0.13

æłª

0.13

wand

0.13

Activations Density 0.032%

imperative phrases that encourage action or decision-making

No Comments

No Known Activations