INDEX

Explanations

references to beliefs, actions, and their alignment or discrepancies

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

ÅĤu

-0.15

 lieu

-0.14

 competing

-0.14

ida

-0.14

iji

-0.14

 Aware

-0.13

utra

-0.13

emento

-0.13

á»Ń

-0.12

 rivalry

-0.12

POSITIVE LOGITS

 match

0.56

 matches

0.53

 align

0.52

match

0.46

-match

0.43

 Align

0.42

 matched

0.42

 MATCH

0.41

align

0.41

 Matches

0.41

Activations Density 0.605%

references to beliefs, actions, and their alignment or discrepancies

No Comments

No Known Activations

references to beliefs, actions, and their alignment or discrepancies

No Comments

No Known Activations