INDEX

Explanations

technical terms and parameters related to software configuration and build processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ANNEL

-0.17

EFF

-0.14

 ìĭ¶

-0.14

field

-0.14

let

-0.14

ener

-0.14

LATED

-0.14

©

-0.14

ig

-0.13

Å¾it

-0.13

POSITIVE LOGITS

0.24

/OR

0.19

_FILENO

0.17

_PTR

0.16

_EDEFAULT

0.15

’S

0.15

rame

0.15

WWW

0.15

KEY

0.14

ãģĤ

0.14

Activations Density 0.146%

technical terms and parameters related to software configuration and build processes

No Comments

No Known Activations