INDEX

Explanations

terms associated with identification and classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

leys

-0.17

otime

-0.16

lili

-0.15

iliar

-0.14

tual

-0.14

ISI

-0.14

entin

-0.14

fait

-0.14

ì²Ļ

-0.14

oney

-0.13

POSITIVE LOGITS

ic

1.12

ically

0.65

ics

0.65

IC

0.63

(ic

0.51

ic

0.51

iÄĩ

0.45

ica

0.45

icum

0.43

icz

0.43

Activations Density 0.116%

terms associated with identification and classification

No Comments

No Known Activations