INDEX

Explanations

organizational names and their missions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rending

-0.16

 tally

-0.15

utton

-0.15

SEE

-0.15

Ã¤d

-0.15

 Hairst

-0.14

ijkstra

-0.14

antic

-0.14

haps

-0.14

uary

-0.14

POSITIVE LOGITS

 edin

0.15

RetVal

0.14

tearDown

0.14

 superClass

0.14

punk

0.13

å¦»

0.13

esinin

0.13

 Leak

0.13

Activations Density 0.066%

organizational names and their missions

No Comments

No Known Activations