INDEX

Explanations

references to the name "Gibson" and variations of it across different contexts

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

iske

-0.15

ynes

-0.15

ablish

-0.14

atsu

-0.14

ingen

-0.14

apa

-0.14

restriction

-0.14

ingu

-0.14

branches

-0.14

numer

-0.14

POSITIVE LOGITS

bons

0.23

riel

0.18

untu

0.18

ault

0.17

bon

0.16

erty

0.16

ilter

0.16

ity

0.15

oney

0.14

Activations Density 0.013%

references to the name "Gibson" and variations of it across different contexts

No Comments

No Known Activations