INDEX

Explanations

connective phrases indicating progression or continuity in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.16

 Interpret

-0.16

si

-0.14

 perceived

-0.14

interpret

-0.14

ilon

-0.14

ussed

-0.14

 Perception

-0.13

ings

-0.13

AME

-0.13

POSITIVE LOGITS

 hearing

0.52

 hear

0.46

 Hearing

0.42

hear

0.42

 hears

0.39

 knowing

0.38

 know

0.37

 Hear

0.35

know

0.35

 heard

0.34

Activations Density 0.018%

connective phrases indicating progression or continuity in narratives

No Comments

No Known Activations