INDEX

Explanations

references to cocktails and drinks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

%p

-0.15

 GOODMAN

-0.15

ÎŃÎ»

-0.15

 cooker

-0.14

_USERNAME

-0.14

.Context

-0.14

lander

-0.13

 bake

-0.13

.Transactional

-0.13

breadcrumb

-0.13

POSITIVE LOGITS

 served

0.17

-serving

0.16

ìŀĶ

0.15

jing

0.15

 glasses

0.15

deniz

0.14

uis

0.14

serve

0.14

 bartender

0.14

Activations Density 0.037%

references to cocktails and drinks

No Comments

No Known Activations