INDEX

Explanations

references to picnics and associated activities

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

èĪª

-0.17

utor

-0.15

habit

-0.15

 downstairs

-0.14

ukt

-0.14

ULATOR

-0.14

soever

-0.14

 gece

-0.14

ids

-0.13

eldom

-0.13

POSITIVE LOGITS

pic

0.56

 picnic

0.55

Pic

0.51

-pic

0.49

pic

0.48

Pic

0.47

PIC

0.41

.pic

0.35

PIC

0.35

_pic

0.33

Activations Density 0.160%

references to picnics and associated activities

No Comments

No Known Activations