INDEX

Explanations

references to locations or significant figures within a cultural or historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ping

-0.15

 Nigerian

-0.15

ulkan

-0.15

 quoi

-0.14

InBackground

-0.14

BackStack

-0.14

ulan

-0.14

mall

-0.14

İ·

-0.14

unos

-0.14

POSITIVE LOGITS

à½

0.29

dz

0.25

Bh

0.23

lh

0.23

 Doch

0.21

 Trong

0.20

à¼

0.20

 Trash

0.18

Trong

0.18

Dor

0.18

Activations Density 0.007%

references to locations or significant figures within a cultural or historical context

No Comments

No Known Activations