INDEX

Explanations

details related to events and their locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

enci

-0.15

ovky

-0.14

Ð¾Ð±Ð¸

-0.14

FAULT

-0.13

ADX

-0.13

oog

-0.13

Ð¸ÑĨÐ¸Ð½

-0.13

à¸±à¸Ļà¸§

-0.13

ÎĪ

-0.13

hack

-0.13

POSITIVE LOGITS

cam

1.48

Cam

1.44

Cam

1.35

CAM

1.26

cam

1.26

CAM

1.13

.cam

1.12

 cams

1.06

_cam

1.06

(cam

1.05

Activations Density 0.066%

details related to events and their locations

No Comments

No Known Activations