INDEX

Explanations

possessive pronouns indicating ownership or affiliation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

//{{

-0.19

lav

-0.18

haus

-0.17

Äįer

-0.16

lava

-0.15

otten

-0.15

upro

-0.15

oucher

-0.15

opard

-0.14

POSITIVE LOGITS

 cues

0.27

cue

0.25

 chances

0.21

Cue

0.21

 Ð´ÐµÐ»Ð¾

0.20

Seat

0.20

cue

0.20

 seat

0.19

 leave

0.19

 Seat

0.18

Activations Density 0.011%

possessive pronouns indicating ownership or affiliation

No Comments

No Known Activations