INDEX

Explanations

elements related to identity changes and transformation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

McA

-0.16

ulp

-0.15

uke

-0.14

abelle

-0.14

 Measures

-0.14

wel

-0.14

ences

-0.14

 Lump

-0.14

itm

-0.13

Mid

-0.13

POSITIVE LOGITS

razier

0.15

éĻħ

0.15

AndPassword

0.14

iÄįky

0.14

icken

0.14

ãĥ³ãĤ¯

0.14

alis

0.14

Specifier

0.14

lÃ©m

0.14

.getDefault

0.13

Activations Density 0.488%

elements related to identity changes and transformation in various contexts

No Comments

No Known Activations