INDEX

Explanations

repetitions of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

åł´

-0.16

ular

-0.15

avic

-0.14

 Cole

-0.14

á»±c

-0.14

arris

-0.14

à¸¢à¸²à¸¢

-0.14

fe

-0.14

lie

-0.13

Ð°ÑĢÑĤ

-0.13

POSITIVE LOGITS

iges

0.16

Scr

0.16

etimes

0.15

LETE

0.14

emie

0.14

ets

0.14

lessly

0.14

iggins

0.14

ensively

0.13

Activations Density 0.013%

repetitions of the word "of."

No Comments

No Known Activations