INDEX

Explanations

phrases indicating causation or results related to events or policies

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

urtle

-0.16

uden

-0.13

ç©´

-0.13

bourg

-0.12

_lifetime

-0.12

utz

-0.12

urtles

-0.12

EFA

-0.12

arges

-0.12

ÏĦÎ±ÏĤ

-0.12

POSITIVE LOGITS

 result

0.52

 product

0.48

 consequence

0.43

product

0.40

 products

0.39

result

0.37

-product

0.35

 outcome

0.35

 culmination

0.34

 RESULT

0.34

Activations Density 0.218%

phrases indicating causation or results related to events or policies

No Comments

No Known Activations