INDEX

Explanations

possessive pronouns and their related modifiers

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

owo

-0.18

cky

-0.16

inus

-0.15

eva

-0.15

_RENDERER

-0.15

NX

-0.15

ERGE

-0.15

stk

-0.14

foon

-0.14

sx

-0.14

POSITIVE LOGITS

 quest

0.20

bid

0.19

 spare

0.18

 attempts

0.18

 attempt

0.18

 effort

0.17

 absence

0.17

 teens

0.17

 lifetime

0.16

 Pill

0.16

Activations Density 0.109%

possessive pronouns and their related modifiers

No Comments

No Known Activations