INDEX

Explanations

names and surnames, particularly those with specific endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

amer

-0.17

leton

-0.17

ermann

-0.17

ichi

-0.16

emer

-0.15

.sul

-0.15

ibal

-0.15

 Mutation

-0.14

alu

-0.14

ponce

-0.14

POSITIVE LOGITS

rosso

0.15

 hale

0.14

VID

0.14

.simps

0.14

rub

0.14

Tut

0.14

bud

0.13

Aub

0.13

 sÆ¡

0.13

++.

0.13

Activations Density 0.004%

names and surnames, particularly those with specific endings

No Comments

No Known Activations