INDEX

Explanations

references to ice and frozen items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ã¡c

-0.16

abbit

-0.16

 super

-0.15

 understand

-0.15

 narration

-0.15

itech

-0.15

 trif

-0.14

ective

-0.14

GA

-0.14

Į¨

-0.14

POSITIVE LOGITS

lush

0.17

ois

0.16

arsi

0.16

FRING

0.16

isel

0.15

igital

0.15

'gc

0.15

oti

0.15

imli

0.14

ebi

0.14

Activations Density 0.021%

references to ice and frozen items

No Comments

No Known Activations