INDEX

Explanations

code segments involving variable assignments and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ctl

-0.16

aje

-0.15

hip

-0.15

biology

-0.14

hip

-0.14

 Viol

-0.14

.scalablytyped

-0.13

Hip

-0.13

POSITIVE LOGITS

 Bars

0.17

ÐµÑĢÐ°Ñħ

0.15

alla

0.15

iman

0.15

ird

0.15

èĪĴ

0.14

@}

0.14

 à¤¬à¤¸

0.14

 ÎºÏį

0.14

chin

0.14

Activations Density 0.330%

code segments involving variable assignments and function definitions

No Comments

No Known Activations