INDEX

Explanations

expressions of enjoyment and pleasure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

edes

-0.16

-0.14

Lew

-0.14

ziej

-0.14

Cra

-0.14

ismet

-0.14

-0.13

POSITIVE LOGITS

 mole

0.16

ãĥĬãĥ¼

0.15

Î¯Î´

0.15

.ali

0.15

.ibm

0.14

ãĥ§

0.14

elta

0.14

mmc

0.14

éļĨ

0.14

czy

0.14

Activations Density 0.029%

expressions of enjoyment and pleasure

No Comments

No Known Activations