INDEX

Explanations

numerical data related to measurements and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

#:

-0.15

adder

-0.14

#:

-0.14

 Serialized

-0.13

 Dayton

-0.13

PUR

-0.13

LD

-0.12

 Millenn

-0.12

Unused

-0.12

 Lage

-0.12

POSITIVE LOGITS

atif

0.16

rÃ¼n

0.14

lej

0.14

ifa

0.14

äººæīį

0.14

oley

0.14

iyon

0.13

Ã¡o

0.13

sz

0.13

raya

0.13

Activations Density 0.098%

numerical data related to measurements and statistics

No Comments

No Known Activations