INDEX

Explanations

words and phrases related to discourse and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ë¬¼

-0.15

Hir

-0.14

ãĥ¼ãĤ¹

-0.14

ously

-0.14

ieri

-0.14

 Roller

-0.14

ispens

-0.14

icari

-0.14

aina

-0.14

TEGER

-0.14

POSITIVE LOGITS

ÙĨÚ¯

0.17

çĶ²

0.16

ONS

0.15

erville

0.15

oning

0.15

Î¸Î¹

0.14

 onAnimation

0.14

reau

0.14

à¹Ģà¸ģà¸Ńà¸£

0.14

 minded

0.14

Activations Density 0.042%

words and phrases related to discourse and communication

No Comments

No Known Activations