INDEX

Explanations

expressions of aspiration and achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 triumph

-0.18

 trium

-0.16

uin

-0.16

keiten

-0.15

hol

-0.15

ENCH

-0.15

edom

-0.15

 defaultCenter

-0.14

.LoadScene

-0.14

LIK

-0.14

POSITIVE LOGITS

 attempt

0.23

TRY

0.21

Try

0.21

 attempted

0.21

 Attempt

0.20

 attempts

0.19

 tries

0.18

Attempt

0.18

nob

0.18

try

0.18

Activations Density 0.176%

expressions of aspiration and achievement

No Comments

No Known Activations