INDEX

Explanations

numerical references and evaluation metrics

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

he

-0.14

çŃ

-0.14

ital

-0.14

zb

-0.13

 cand

-0.13

 pick

-0.13

 Pick

-0.13

chter

-0.13

unk

-0.13

hut

-0.13

POSITIVE LOGITS

DMIN

0.17

oÅ¾

0.15

uÄį

0.15

inton

0.15

/WebAPI

0.15

raid

0.14

#:

0.14

atto

0.14

ëª¬

0.14

ighbor

0.13

Activations Density 0.002%

numerical references and evaluation metrics

No Comments

No Known Activations