INDEX

Explanations

function definitions and related programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

mant

-0.15

ead

-0.14

immer

-0.14

omatic

-0.14

izo

-0.13

/rfc

-0.13

 Ð¾Ð±ÑıÐ·Ð°Ð½

-0.13

ByExample

-0.13

á»ĵ

-0.13

ories

-0.13

POSITIVE LOGITS

Î¼Î¯

0.16

UED

0.15

quist

0.15

haps

0.15

oden

0.15

UBE

0.14

dorf

0.14

hal

0.14

ki

0.14

AVED

0.14

Activations Density 0.098%

function definitions and related programming constructs

No Comments

No Known Activations