INDEX

Explanations

the character "Madeleine" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

_Panel

-0.16

ÏĦÏģÎ¹

-0.15

Ð¿ÑĢÐ°Ð²

-0.14

 ëĭ

-0.14

SelectionMode

-0.14

acco

-0.14

ochen

-0.14

 complement

-0.14

wel

-0.14

enstein

-0.14

POSITIVE LOGITS

ulos

0.17

linkplain

0.17

ivos

0.15

ÑĪÐµÐ²

0.14

ville

0.14

 Ð²ÑģÐµÐ³Ð¾

0.14

Ã¡nt

0.14

athers

0.14

ecure

0.14

Activations Density 0.006%

the character "Madeleine" across various contexts

No Comments

No Known Activations