INDEX

Explanations

occurrences of the word "Buffalo" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ustry

-0.16

orial

-0.15

wend

-0.15

azole

-0.15

à¸²à¸ĩ

-0.14

stry

-0.14

egl

-0.14

ÃŃr

-0.14

ugs

-0.14

archy

-0.14

POSITIVE LOGITS

alo

0.19

oon

0.19

oons

0.18

edReader

0.17

eting

0.16

ett

0.16

kich

0.16

ertools

0.15

ets

0.15

ãĥŃãĥ¼

0.15

Activations Density 0.007%

occurrences of the word "Buffalo" and its variants

No Comments

No Known Activations