INDEX

Explanations

conditional phrases indicating hypothetical situations or choices

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

iese

-0.16

 å·Ŀ

-0.16

orsk

-0.15

hausen

-0.13

rear

-0.13

ession

-0.13

Mes

-0.13

 compens

-0.13

yntax

-0.13

 Coal

-0.13

POSITIVE LOGITS

ATCH

0.17

ound

0.15

ãĤ©

0.15

aca

0.15

Ð¾Ð±Ð¸

0.14

ãĤ¦ãĥ³

0.14

Ø®ÙĦ

0.14

umb

0.14

uno

0.14

allel

0.14

Activations Density 0.303%

conditional phrases indicating hypothetical situations or choices

No Comments

No Known Activations