INDEX

Explanations

significant phrases and structures in sentences, particularly those that suggest direction or reference

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

.br

-0.15

ould

-0.15

↵

-0.15

fa

-0.15

.cn

-0.14

owie

-0.14

roph

-0.14

empt

-0.14

fa

-0.14

ear

-0.14

POSITIVE LOGITS

 Ù¾ÙĪØ³Øª

0.15

chw

0.14

ktop

0.14

ebe

0.14

çĢ¬

0.14

SURE

0.14

sink

0.14

mam

0.14

inflate

0.13

ICES

0.13

Activations Density 0.206%

significant phrases and structures in sentences, particularly those that suggest direction or reference

No Comments

No Known Activations