INDEX

Explanations

questions that seek guidance or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 rewritten

-0.15

ober

-0.14

aghan

-0.13

oultry

-0.13

Ð´ÐµÑĤ

-0.13

_Util

-0.12

ØŃÙħ

-0.12

èª

-0.12

haps

-0.12

POSITIVE LOGITS

cheid

0.16

ANDOM

0.15

kee

0.15

AREST

0.15

sgi

0.14

 GenerationType

0.14

((((

0.14

.onView

0.14

å¯¼

0.13

copyright

0.13

Activations Density 0.058%

questions that seek guidance or information

No Comments

No Known Activations