INDEX

Explanations

references to specific historical figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

à¸Ĭà¸²à¸ķ

-0.17

ozem

-0.16

ÑĢÐ¾Ð¸Ð·

-0.15

haps

-0.15

Ä±ma

-0.14

itus

-0.14

 hete

-0.14

 vrou

-0.14

Ä±

-0.14

âĢ¦↵↵↵

-0.13

POSITIVE LOGITS

ober

0.16

ishi

0.16

inside

0.16

 inside

0.15

INGTON

0.15

 offline

0.14

 Malk

0.14

allah

0.14

ern

0.14

imin

0.14

Activations Density 0.049%

references to specific historical figures and events

No Comments

No Known Activations