INDEX

Explanations

phrases indicating direct connections or actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

#ac

-0.15

atre

-0.15

ester

-0.15

 mere

-0.15

IEW

-0.15

TEGER

-0.15

ReadStream

-0.15

ena

-0.14

ENA

-0.14

andra

-0.14

POSITIVE LOGITS

direct

0.21

 direct

0.21

 Direct

0.20

Direct

0.20

 directly

0.20

DIRECT

0.17

_direct

0.17

 diret

0.16

 DIRECT

0.16

_DIRECT

0.16

Activations Density 0.079%

phrases indicating direct connections or actions

No Comments

No Known Activations