INDEX

Explanations

mentions of specific locations, particularly related to historical or notable buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

kening

-0.17

alink

-0.16

Sof

-0.15

.decor

-0.15

Ã³nica

-0.14

steam

-0.14

mbH

-0.14

ÑĥÑĩÐ°

-0.14

ouns

-0.14

unami

-0.14

POSITIVE LOGITS

ault

0.25

aud

0.21

oux

0.21

ot

0.21

ign

0.20

anges

0.19

aye

0.19

ard

0.19

iers

0.18

isson

0.18

Activations Density 0.170%

mentions of specific locations, particularly related to historical or notable buildings

No Comments

No Known Activations