INDEX

Explanations

pronouns that indicate possession or reference to something or someone

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

emme

-0.15

ildo

-0.15

_FIX

-0.14

olib

-0.14

imar

-0.14

eneg

-0.14

 çŃ

-0.14

Ð»Ð¸Ð¼

-0.14

ilt

-0.14

egg

-0.14

POSITIVE LOGITS

esson

0.20

 alive

0.17

alive

0.15

-active

0.15

pla

0.14

andler

0.14

ardy

0.14

 Ð³ÐµÑĢ

0.14

ĸ

0.14

Activations Density 0.030%

pronouns that indicate possession or reference to something or someone

No Comments

No Known Activations