INDEX

Explanations

mentions of the letter 'Z'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

hazi

-0.17

DAQ

-0.16

hv

-0.15

ELLOW

-0.15

 Gujar

-0.15

Ĺi

-0.14

ãĤ·ãĥ£

-0.14

ÄĽÅ¾

-0.14

 Spicer

-0.14

ifax

-0.14

POSITIVE LOGITS

ebo

0.18

 glob

0.15

adem

0.15

glob

0.15

emes

0.15

iles

0.14

ach

0.14

aren

0.14

eman

0.14

BED

0.14

Activations Density 0.017%

mentions of the letter 'Z'

No Comments

No Known Activations