INDEX

Explanations

references to physical environments and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Alone

-0.16

å¤®

-0.15

Han

-0.15

ediator

-0.14

antee

-0.14

ellow

-0.14

 Parallel

-0.14

 Celebrity

-0.14

jal

-0.14

 Solo

-0.14

POSITIVE LOGITS

_RC

0.15

umbed

0.14

>Error

0.14

gui

0.14

CKER

0.14

CTL

0.14

 ì²ĺ

0.13

iox

0.13

gid

0.13

èŃ

0.13

Activations Density 0.449%

references to physical environments and their descriptions

No Comments

No Known Activations