INDEX

Explanations

keywords or phrases associated with technical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulk

-0.18

ijkstra

-0.17

.dsl

-0.17

ikon

-0.16

DEX

-0.16

etto

-0.15

ÙĦÙī

-0.15

iko

-0.15

ye

-0.15

º

-0.14

POSITIVE LOGITS

kee

0.17

Mor

0.15

Mor

0.14

Hem

0.14

_CONFIG

0.14

 Moral

0.14

ssel

0.14

aks

0.14

MOR

0.14

dom

0.14

Activations Density 0.031%

keywords or phrases associated with technical or scientific contexts

No Comments

No Known Activations