INDEX

Explanations

repeated mentions of the name "Kent."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

melon

-0.17

keit

-0.15

geh

-0.15

ãĥ³ãĥī

-0.14

regon

-0.14

bit

-0.14

ce

-0.14

ifestyles

-0.14

istics

-0.14

aturas

-0.14

POSITIVE LOGITS

ucky

0.31

aro

0.21

ertainment

0.17

mere

0.17

une

0.17

lage

0.17

ampo

0.16

istry

0.16

ekli

0.16

Activations Density 0.006%

repeated mentions of the name "Kent."

No Comments

No Known Activations