INDEX

Explanations

terms related to pitching ideas or concepts

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

amba

-0.16

Ìĥ

-0.16

/mit

-0.15

 flushed

-0.15

isch

-0.15

 addCriterion

-0.14

 puzz

-0.14

 flushing

-0.14

enda

-0.14

niest

-0.14

POSITIVE LOGITS

fork

0.50

 fork

0.26

 Fork

0.23

 forks

0.22

 deck

0.20

 Pitch

0.19

pitch

0.19

deck

0.19

 pitch

0.19

 decks

0.18

Activations Density 0.007%

terms related to pitching ideas or concepts

No Comments

No Known Activations