INDEX

Explanations

phrases indicating direct interactions or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Ð¸Ð½ÐºÑĥ

-0.15

klad

-0.15

 grace

-0.14

ingen

-0.14

.metro

-0.14

 Ð¾Ð´Ð½Ð¾Ð²

-0.14

ubat

-0.14

richt

-0.14

 traps

-0.13

aret

-0.13

POSITIVE LOGITS

 directly

0.35

direct

0.21

 Direct

0.18

Direct

0.17

enville

0.17

.direct

0.17

 diret

0.17

 DIRECT

0.16

zeitig

0.16

irect

0.16

Activations Density 0.032%

phrases indicating direct interactions or connections

No Comments

No Known Activations