INDEX

Explanations

proper nouns, particularly the names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lez

-0.17

 Spicer

-0.15

ambre

-0.15

pson

-0.14

 Davidson

-0.14

LOB

-0.14

HELL

-0.14

 double

-0.13

iselect

-0.13

Î»ÎµÎ¯

-0.13

POSITIVE LOGITS

adel

0.19

arie

0.16

inks

0.16

egan

0.15

brig

0.15

 Rooney

0.14

toPromise

0.14

adh

0.14

.jsx

0.14

ode

0.14

Activations Density 0.008%

proper nouns, particularly the names of individuals

No Comments

No Known Activations