INDEX

Explanations

references to the name "Carol" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oise

-0.17

ovice

-0.16

ayet

-0.16

plier

-0.15

strup

-0.15

oxy

-0.15

etary

-0.15

andon

-0.15

Ð¾Ð´Ð¾

-0.14

ched

-0.14

POSITIVE LOGITS

Ann

0.19

thers

0.18

Ann

0.16

lee

0.15

ynn

0.15

les

0.15

Sue

0.15

lo

0.15

led

0.15

anne

0.15

Activations Density 0.005%

references to the name "Carol" and its variations in different contexts

No Comments

No Known Activations