INDEX

Explanations

terms related to web technologies and their applications

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

iasi

-0.19

anto

-0.17

ince

-0.16

 McInt

-0.15

ends

-0.15

encil

-0.15

sono

-0.14

_RD

-0.14

uco

-0.14

asz

-0.14

POSITIVE LOGITS

zb

0.17

osphere

0.15

 subt

0.14

ella

0.14

sumer

0.14

 particular

0.14

 numRows

0.13

enna

0.13

nable

0.13

Activations Density 0.499%

terms related to web technologies and their applications

No Comments

No Known Activations