INDEX

Explanations

numerical data and specific measurements related to locations and timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ittel

-0.19

 GenerationType

-0.16

edor

-0.15

vect

-0.15

halt

-0.15

ereum

-0.15

isel

-0.15

quette

-0.14

 çĶŁåĳ½åĳ¨æľŁ

-0.14

/stdc

-0.13

POSITIVE LOGITS

 alike

0.18

 respectively

0.17

engl

0.15

 Mend

0.14

aug

0.14

å§

0.14

 cast

0.14

 olmayan

0.14

ouden

0.13

 Angelo

0.13

Activations Density 0.174%

numerical data and specific measurements related to locations and timelines

No Comments

No Known Activations