INDEX

Explanations

references to mathematical inequalities and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

resco

-0.15

ictionary

-0.14

edList

-0.14

elt

-0.14

ÑīÐ¸Ð½Ð°

-0.14

zon

-0.14

íĻ©

-0.14

ÅĻeba

-0.14

uzz

-0.13

POSITIVE LOGITS

EOF

0.15

CREMENT

0.14

iez

0.14

rei

0.14

undle

0.14

 æŁ

0.14

 given

0.14

age

0.14

/pkg

0.13

odom

0.13

Activations Density 0.331%

references to mathematical inequalities and variables

No Comments

No Known Activations