INDEX

Explanations

uppercase 'L' characters or similar symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Tib

-0.15

é¤

-0.15

linger

-0.14

roti

-0.14

 Haven

-0.14

ahn

-0.14

spb

-0.14

AINS

-0.14

uffix

-0.13

isl

-0.13

POSITIVE LOGITS

igue

0.33

iga

0.27

azio

0.25

uka

0.24

atics

0.23

oris

0.21

akers

0.19

lor

0.19

ion

0.19

FP

0.19

Activations Density 0.008%

uppercase 'L' characters or similar symbols

No Comments

No Known Activations