INDEX

Explanations

terms related to blindness and sight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

CppClass

-0.17

alue

-0.14

wayne

-0.14

BackStack

-0.13

ains

-0.13

 ç©

-0.13

 çŃ

-0.13

isposable

-0.13

lemetry

-0.13

zzle

-0.13

POSITIVE LOGITS

fold

0.18

+len

0.16

rn

0.15

0.14

itia

0.14

 Ãľl

0.14

/bl

0.14

CCI

0.14

 Gast

0.13

 usual

0.13

Activations Density 0.035%

terms related to blindness and sight

No Comments

No Known Activations