INDEX

Explanations

references to problematic experiences or memories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ipp

-0.17

iÃ£o

-0.16

ile

-0.15

 Ã¶l

-0.14

 Vale

-0.14

ead

-0.14

iac

-0.14

 Headquarters

-0.14

Î´Î¬

-0.14

POSITIVE LOGITS

otu

0.17

reas

0.16

Strings

0.15

tring

0.15

otti

0.15

abama

0.15

adolu

0.15

CLU

0.15

vet

0.14

áº©n

0.14

Activations Density 0.001%

references to problematic experiences or memories

No Comments

No Known Activations