INDEX

Explanations

numeric values and measurements, particularly in the context of statistical data or specifications

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

meni

-0.17

ledged

-0.15

InView

-0.14

agher

-0.14

ampion

-0.14

.toolbox

-0.14

readcrumbs

-0.14

erral

-0.14

imuth

-0.13

 Singular

-0.13

POSITIVE LOGITS

Pip

0.16

unya

0.15

hta

0.15

 Odin

0.15

 Duch

0.14

 invisible

0.14

VIRTUAL

0.14

_uart

0.13

.undefined

0.13

-equ

0.13

Activations Density 0.090%

numeric values and measurements, particularly in the context of statistical data or specifications

No Comments

No Known Activations