INDEX

Explanations

phrases regarding conditional statements and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eneg

-0.17

 Kelly

-0.15

ais

-0.14

 Cand

-0.14

aise

-0.14

 Tanner

-0.14

 GÃ¼r

-0.13

 MÃ©

-0.13

ia

-0.13

far

-0.13

POSITIVE LOGITS

kus

0.19

[it

0.17

à¤¾:

0.16

å®ĥ

0.15

Ø§ÙĪØª

0.15

Î³ÎºÎ±

0.14

çĵľ

0.14

abar

0.14

:animated

0.14

awy

0.14

Activations Density 0.159%

phrases regarding conditional statements and classifications

No Comments

No Known Activations