INDEX

Explanations

names of individuals associated with various achievements or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_coeffs

-0.15

Ã©ny

-0.14

eous

-0.14

 trag

-0.14

iac

-0.13

 gÃ©

-0.13

ENE

-0.13

 matters

-0.13

erde

-0.13

 Matters

-0.13

POSITIVE LOGITS

ector

0.16

 Vest

0.14

 ragaz

0.14

áŀ¶áŀ

0.14

 buddy

0.13

Dot

0.13

nop

0.13

otlin

0.13

ernel

0.13

.Strings

0.13

Activations Density 0.246%

names of individuals associated with various achievements or events

No Comments

No Known Activations