INDEX

Explanations

mentions of the name "Teresa" or similar variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iscard

-0.15

ippi

-0.15

/loose

-0.15

iliary

-0.15

æĿ¾

-0.14

omat

-0.14

ayar

-0.14

adÃŃ

-0.14

stay

-0.14

et

-0.14

POSITIVE LOGITS

0.17

±Ð¾ÑĤ

0.15

wdx

0.14

.fin

0.14

Pooling

0.14

_revision

0.14

 meant

0.13

terdam

0.13

Activations Density 0.001%

mentions of the name "Teresa" or similar variations

No Comments

No Known Activations