INDEX

Explanations

references to personal experiences and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

chten

-0.15

asa

-0.15

lags

-0.14

ä½ľ

-0.14

ocator

-0.13

 rethink

-0.13

 èŃ

-0.13

adan

-0.13

cpy

-0.13

POSITIVE LOGITS

 sitting

0.28

 walk

0.28

sit

0.28

 step

0.27

 standing

0.27

 stepping

0.25

 Walk

0.25

walk

0.25

 walked

0.25

 walks

0.25

Activations Density 0.258%

references to personal experiences and emotions

No Comments

No Known Activations