INDEX

Explanations

occurrences of conditional phrases and discussions about decision-making scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

iaux

-0.15

èŀº

-0.14

 Miracle

-0.14

ãĤ¯ãĤ·ãĥ§ãĥ³

-0.14

APPER

-0.14

çĽĬ

-0.14

elpers

-0.14

çĽŁ

-0.14

RowAt

-0.14

bsd

-0.13

POSITIVE LOGITS

 then

0.60

then

0.54

 THEN

0.49

 Then

0.49

 ÑĤÐ¾Ð³Ð´Ð°

0.48

 entonces

0.47

Then

0.46

THEN

0.42

	then

0.41

 entÃ£o

0.39

Activations Density 0.265%

occurrences of conditional phrases and discussions about decision-making scenarios

No Comments

No Known Activations