INDEX

Explanations

technical specifications and references related to software and programming environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

à¥ģà¤·

-0.17

auer

-0.17

ifax

-0.15

ensa

-0.15

avi

-0.15

IRO

-0.15

ivy

-0.15

edii

-0.14

 Principal

-0.14

odi

-0.14

POSITIVE LOGITS

WXYZ

0.18

è¶³

0.15

 Gamb

0.15

ortic

0.14

redicate

0.14

(defvar

0.14

.rpc

0.13

ViewById

0.13

han

0.13

Activations Density 0.049%

technical specifications and references related to software and programming environments

No Comments

No Known Activations