INDEX

Explanations

occurrences of numerical values and lists within technical or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

igg

-0.17

ÅĽ

-0.15

ANS

-0.15

Intialized

-0.15

âĢ¦

-0.15

-↵

-0.15

fat

-0.14

fillType

-0.14

_hdl

-0.14

ittel

-0.14

POSITIVE LOGITS

untu

0.17

iram

0.16

lia

0.14

aday

0.14

lla

0.14

enso

0.14

alia

0.13

ows

0.13

abi

0.13

iá»ĥu

0.13

Activations Density 0.123%

occurrences of numerical values and lists within technical or programming contexts

No Comments

No Known Activations