INDEX

Explanations

actions related to drinking or consuming beverages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

igham

-0.15

 inactive

-0.15

 Quant

-0.14

éĥ

-0.14

iris

-0.14

addock

-0.14

wards

-0.14

irling

-0.13

ider

-0.13

POSITIVE LOGITS

tha

0.16

umd

0.15

abcdefghijkl

0.14

/question

0.14

dden

0.14

raÄį

0.14

shint

0.13

pton

0.13

.UIManager

0.13

agenta

0.13

Activations Density 0.009%

actions related to drinking or consuming beverages

No Comments

No Known Activations