INDEX

Explanations

geographical locations and distances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MAND

-0.15

æĺĩ

-0.14

REFIX

-0.13

Ã¤m

-0.13

ÙĤÙħ

-0.13

maid

-0.13

mando

-0.13

æľĽ

-0.13

POSITIVE LOGITS

lh

0.18

avr

0.17

enha

0.16

untu

0.15

ynes

0.14

ruh

0.14

lv

0.14

ĩ

0.14

ruary

0.14

heim

0.14

Activations Density 0.011%

geographical locations and distances

No Comments

No Known Activations