INDEX

Explanations

connections between phrases or clauses in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 even

-0.18

 EVEN

-0.14

intent

-0.14

esian

-0.14

evenodd

-0.13

Fetcher

-0.13

least

-0.13

even

-0.13

undef

-0.13

 Burton

-0.13

POSITIVE LOGITS

raquo

0.21

/or

0.21

ROID

0.19

rew

0.19

/of

0.18

 alike

0.17

Beyond

0.16

REW

0.16

 Ð´ÑĢÑĥÐ³Ð¸Ðµ

0.15

rogen

0.15

Activations Density 0.270%

connections between phrases or clauses in a text

No Comments

No Known Activations