INDEX

Explanations

numerical and statistical information related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

idal

-0.16

uire

-0.15

 vide

-0.15

al

-0.15

 global

-0.14

 strategy

-0.14

ton

-0.14

in

-0.14

CI

-0.14

dec

-0.14

POSITIVE LOGITS

vyk

0.16

 anale

0.15

ExecutionContext

0.15

 WINAPI

0.14

opup

0.14

OMATIC

0.14

 seedu

0.14

ÏĦÏį

0.14

.sul

0.14

ksam

0.14

Activations Density 0.922%

numerical and statistical information related to various contexts

No Comments

No Known Activations