INDEX

Explanations

phrases indicating expectation or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

deaux

-0.17

ãĤŃãĥ¼

-0.16

ioni

-0.15

otten

-0.15

ritis

-0.15

essen

-0.14

ahrenheit

-0.14

ushima

-0.14

ruz

-0.14

 seat

-0.14

POSITIVE LOGITS

Try

0.30

try

0.27

TRY

0.27

Try

0.27

 tried

0.25

try

0.24

 tries

0.23

TRY

0.22

_try

0.22

 trying

0.21

Activations Density 0.010%

phrases indicating expectation or potential outcomes

No Comments

No Known Activations