INDEX

Explanations

references to the name "Margaret."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ivil

-0.17

 cÆ¡

-0.17

ernet

-0.16

andas

-0.15

 Meadows

-0.15

ÐºÑĤÐ°

-0.15

enburg

-0.15

hall

-0.14

langs

-0.14

POSITIVE LOGITS

son

0.19

amma

0.16

tright

0.15

oren

0.15

orc

0.15

otos

0.15

ty

0.15

cone

0.14

boro

0.14

utes

0.14

Activations Density 0.005%

references to the name "Margaret."

No Comments

No Known Activations