INDEX

Explanations

mentions of the name "Alice"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

eros

-0.19

-0.15

 Mish

-0.15

erval

-0.15

_Impl

-0.15

ingt

-0.15

upertino

-0.14

uman

-0.14

YTE

-0.14

Ãº

-0.14

POSITIVE LOGITS

 Springs

0.24

 Cooper

0.18

 springs

0.18

aus

0.17

heimer

0.17

onso

0.16

amma

0.15

Î¹Î²

0.15

urette

0.15

 æĺ¥

0.15

Activations Density 0.006%

mentions of the name "Alice"

No Comments

No Known Activations