INDEX

Explanations

location names and references related to geographic regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rary

-0.16

elerik

-0.16

agma

-0.15

ä¿º

-0.14

Ä±rak

-0.14

ãģĵãĤį

-0.14

Nem

-0.14

prints

-0.14

_tl

-0.14

owie

-0.14

POSITIVE LOGITS

ogo

0.15

aul

0.14

toa

0.14

'])?

0.13

fol

0.13

iÅ¾

0.13

warts

0.13

ometr

0.13

 brav

0.13

 derog

0.13

Activations Density 1.163%

location names and references related to geographic regions

No Comments

No Known Activations