INDEX

Explanations

references to specific groups of people and their communication or publication efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

otte

-0.17

 codes

-0.16

-0.15

asso

-0.15

 Ø¬Ø²

-0.14

enef

-0.14

indicator

-0.14

 Codes

-0.14

ãĤ¯ãĤ»

-0.14

abin

-0.14

POSITIVE LOGITS

LING

0.16

acman

0.14

tparam

0.14

 Wilderness

0.14

mana

0.14

 Transformer

0.13

ãĤ·ãĥ¼

0.13

 Gotham

0.13

ustin

0.13

acia

0.13

Activations Density 0.094%

references to specific groups of people and their communication or publication efforts

No Comments

No Known Activations