INDEX

Explanations

instances of the letter "D" or its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÐµÐ¼

-0.19

iv

-0.19

à¸²à¸§

-0.18

ay

-0.17

ies

-0.17

ia

-0.17

iaz

-0.17

isch

-0.17

is

-0.17

ivr

-0.17

POSITIVE LOGITS

nip

0.18

elt

0.17

uality

0.17

otted

0.17

iction

0.16

èį

0.16

odo

0.16

hall

0.16

TM

0.15

 Ding

0.15

Activations Density 0.124%

instances of the letter "D" or its variations in various contexts

No Comments

No Known Activations