INDEX

Explanations

technical or operational terms related to equipment and diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ustr

-0.17

usercontent

-0.16

_TA

-0.16

ãĥ©ãĤ¯

-0.15

vester

-0.15

Ð´Ð°Ð½

-0.14

uptools

-0.14

 gross

-0.14

è°±

-0.14

orda

-0.14

POSITIVE LOGITS

gl

0.20

Gl

0.18

otto

0.16

.allocate

0.15

gl

0.15

anic

0.15

Gl

0.15

íĭ°

0.14

arus

0.14

ouri

0.14

Activations Density 0.028%

technical or operational terms related to equipment and diagnostics

No Comments

No Known Activations