INDEX

Explanations

terms related to professional or technical contexts, particularly in mathematics and statistics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-webpack

-0.16

RSS

-0.15

achts

-0.14

isons

-0.14

_cs

-0.14

itere

-0.14

umbnails

-0.14

reme

-0.13

cos

-0.13

POSITIVE LOGITS

aco

0.17

ãĥªãĤ«

0.16

-side

0.15

ayet

0.15

 accordingly

0.14

éĻ½

0.14

coli

0.14

 Side

0.14

.Promise

0.14

zin

0.14

Activations Density 0.027%

terms related to professional or technical contexts, particularly in mathematics and statistics

No Comments

No Known Activations