INDEX

Explanations

phrases indicating a selection or variety of choices available

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÌĨ

-0.15

Ì§

-0.14

EATURE

-0.14

imbus

-0.14

 DeÄŁer

-0.13

mamak

-0.13

lamaya

-0.13

Entered

-0.13

SENS

-0.13

ils

-0.13

POSITIVE LOGITS

 choice

0.90

 choose

0.79

 choices

0.75

choice

0.75

 Choice

0.73

-choice

0.71

 Choose

0.68

choose

0.68

Choice

0.68

 choosing

0.67

Activations Density 0.188%

phrases indicating a selection or variety of choices available

No Comments

No Known Activations