INDEX

Explanations

phrases indicating associations or relationships between multiple elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

oux

-0.16

 lÃ£

-0.16

lyph

-0.16

ibs

-0.15

andas

-0.15

ibe

-0.14

ib

-0.14

Bindings

-0.14

POSITIVE LOGITS

ieri

0.16

unsch

0.16

alar

0.16

 evapor

0.15

TD

0.15

omi

0.15

oppable

0.15

ä¸Ģèµ·

0.14

pread

0.14

bei

0.14

Activations Density 0.176%

phrases indicating associations or relationships between multiple elements

No Comments

No Known Activations