INDEX

Explanations

references to the brand "IBM" and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

igner

-0.17

áº§n

-0.17

angen

-0.17

_tolerance

-0.15

zure

-0.15

Ħĸ

-0.15

ÑĤÑĢÐ¾

-0.15

ÑĢÑıÐ´

-0.15

annon

-0.15

 HÃ¼s

-0.15

POSITIVE LOGITS

upro

0.26

ib

0.22

rahim

0.19

Ã©ric

0.19

IB

0.18

clc

0.18

(ib

0.17

Arc

0.17

_ib

0.16

(IB

0.16

Activations Density 0.007%

references to the brand "IBM" and related terminology

No Comments

No Known Activations